http://cs.gettysburg.edu/ai-matters/api.php?action=feedcontributions&user=ToddNeller&feedformat=atomAI Matters Wiki - User contributions [en]2024-03-29T15:52:24ZUser contributionsMediaWiki 1.26.3http://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=44Resources2018-09-15T18:31:41Z<p>ToddNeller: CTR Prediction resources</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
** [http://www.kdnuggets.com/2017/04/10-free-must-read-books-machine-learning-data-science.html KDNuggets "10 Free Must-Read Books for Machine Learning and Data Science"]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
** [https://ml.berkeley.edu/blog/tutorials/ Berkeley student crash course on ML]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]<br />
==Neural Network Learning==<br />
*Textbooks<br />
** [http://www.deeplearningbook.org/ Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville]<br />
** [http://neuralnetworksanddeeplearning.com/ Michael Nielson's Neural Networks and Deep Learning online book.]<br />
*Websites <br />
** [https://www.facebook.com/groups/DeepNetGroup/ Waikit Lau and Arthur Chan's Artificial Intelligence and Deep Learning (AIDL) Facebook group] and [https://www.facebook.com/groups/DeepNetGroup/permalink/385843868475168/ FAQ]<br />
** [http://yerevann.com/a-guide-to-deep-learning/ A Guide to Deep Learning by YerevaNN Labs]<br />
** [http://p.migdal.pl/2017/04/30/teaching-deep-learning.html Piotr Migdał's Learning Deep Learning with Keras]<br />
** [http://aiplaybook.a16z.com/docs/reference/links a16z team's reference links]<br />
** [http://cs231n.github.io/convolutional-networks/ Stanford's CS 231n Convolutional Networks course website]<br />
** various Wikipedia pages concerning [https://en.wikipedia.org/wiki/Artificial_neural_network artificial neural networks]<br />
** [http://playground.tensorflow.org/ TensorFlow Playground]<br />
** [https://distill.pub/2017/momentum/ Why Momentum Really Works]<br />
** [http://lamda.nju.edu.cn/weixs/project/CNNTricks/CNNTricks.html Xiu-Shen Wei's Must Know Tips/Tricks in Deep Neural Networks]<br />
** [https://medium.com/towards-data-science/secret-sauce-behind-the-beauty-of-deep-learning-beginners-guide-to-activation-functions-a8e23a57d046 Medium.com guide: Understanding Activation Functions]<br />
** [https://github.com/williamFalcon/DeepRLHacks John Schulman's Deep RL Hacks (summarized by William Falcon)]<br />
** [https://blog.waya.ai/deep-residual-learning-9610bb62c355 Michael Dietz's Understand Deep Residual Networks]<br />
*Online Courses<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's Machine Learning course] and [https://www.coursera.org/specializations/deep-learning Coursera Deep Learning specialization]<br />
** [https://www.coursera.org/learn/neural-networks Geoffrey Hinton's Neural Networks for Machine Learning course]<br />
** [http://www.dmi.usherb.ca/~larocheh/neural_networks Hugo Larochelle's graduate-level online Neural Network course]<br />
** [https://medium.freecodecamp.org/dive-into-deep-learning-with-these-23-online-courses-bf247d289cc0 David Venturi's list of Deep Learning online courses]<br />
** [http://thegrandjanitor.com/2016/08/15/learning-deep-learning-my-top-five-resource/ Arthur Chan's top 5]<br />
*Software<br />
** [https://www.tensorflow.org/ TensorFlow] and [https://keras.io/ Keras]<br />
** [https://github.com/Microsoft/cntk Microsoft Cognitive Toolkit (CNTK)]<br />
** [https://github.com/Theano/Theano Theano]<br />
** [http://torch.ch/ Torch] and [http://pytorch.org/ PyTorch])<br />
** [http://caffe.berkeleyvision.org/ Caffe]<br />
** [http://mxnet.io/ MXNet]<br />
** [https://deeplearning4j.org/ DeepLearning4J]<br />
** [https://en.wikipedia.org/wiki/Comparison_of_deep_learning_software Comparison of deep learning software] and [https://twitter.com/fchollet/status/852194634470223873 April 2017 popularity metrics]<br />
*Hardware<br />
** [http://timdettmers.com/2017/04/09/which-gpu-for-deep-learning Tim Dettmers' GPU comparison study]<br />
** [https://d4datascience.wordpress.com/2017/05/06/setting-up-a-gpu-based-deep-learning-machine/ Ved's d4datascience blog entry on setting up a GPU-based deep learning machine]<br />
<br />
=Hidden Markov Models=<br />
* Video Introductions<br />
** [https://youtu.be/mNSQ-prhgsw Daphne Koller's 12-minute video "Template Models: Hidden Markov Models - Stanford University"]<br />
** [https://youtu.be/jY2E6ExLxaw Nando de Freitas' 52-minute UBC lecture "undergraduate machine learning 9: Hidden Markov models - HMM"]<br />
* Texts and Articles<br />
** Russell and Norvig, Artificial Intelligence: a modern approach, 3rd ed, sections 15.3, 20.3.3.<br />
** [https://web.stanford.edu/~jurafsky/slp3/9.pdf Speech and Language Processing, 3rd ed, Chapter 9 by Daniel Jurafsky and James H. Martin]<br />
** [http://www.ece.ucsb.edu/Faculty/Rabiner/ece259/Reprints/tutorial%20on%20hmm%20and%20applications.pdf Lawrence Rabiner tutorial "A tutorial on hidden Markov models and selected applications in speech recognition"]<br />
** Christopher Bishop's "Pattern Recognition and Machine Learning", Section 13.2<br />
** [https://stats.stackexchange.com/questions/3294/resources-for-learning-markov-chain-and-hidden-markov-models StackExchange thread "Resources for learning Markov chain and hidden Markov models"]<br />
* Other Resources<br />
** [https://www.udacity.com/course/intro-to-artificial-intelligence--cs271 Udacity's `"Intro to Artificial Intelligence" course by Peter Norvig and Sebastian Thrun]<br />
** [https://www.udacity.com/course/probabalistic-models--cx27 Udacity's "Artificial Intelligence - Probabalistic Models"]<br />
** [https://www.coursera.org/learn/bioinformatics-pku/lecture/7pbUo/hidden-markov-model Coursera's Ge Gao lecture on HMMs]<br />
** [http://cs.jhu.edu/~jason/papers/eisner.hmm.xls Jason Eisner's spreadsheet for teaching the forward-backward algorithm] and [https://cs.jhu.edu/~jason/papers/eisner.tnlp02.pdf his paper on using it for teaching] <br />
** [https://www.quora.com/What-are-some-good-resources-for-learning-about-Hidden-Markov-Models Quora question "What are some good resources for learning about Hidden Markov Models?"]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
** [http://modelai.gettysburg.edu/2017/hmm Sravana Reddy's "Implementing a Hidden Markov Model Toolkit"]<br />
** [http://modelai.gettysburg.edu/2010/pacman/projects/tracking/busters.html John DeNero and Dan Klein's "The Pac-Man Projects" Project #4: Ghostbusters]<br />
<br />
=Click-Through Rate (CTR) Prediction=<br />
* [https://www.kaggle.com/ Kaggle] CTR Prediction Competitions:<br />
** [https://www.kaggle.com/c/criteo-display-ad-challenge Criteo]<br />
** [https://www.kaggle.com/c/avazu-ctr-prediction Avazu]<br />
** [https://www.kaggle.com/c/avito-context-ad-clicks Avito]<br />
** [https://www.kaggle.com/c/outbrain-click-prediction Outbrain]<br />
* [https://xgboost.readthedocs.io/en/latest/ XGBoost] - Extreme Gradient Tree Boosting<br />
** [https://dl.acm.org/citation.cfm?doid=2939672.2939785 XGBoost: A Scalable Tree Boosting System] <br />
* [https://github.com/guestwalk/libffm libffm] - library for Field-aware Factorization Machines (FFMs)<br />
** [https://dl.acm.org/citation.cfm?doid=2959100.2959134 Field-aware factorization machines for CTR prediction]<br />
** [https://www.csie.ntu.edu.tw/~r01922136/kaggle-2014-criteo.pdf Slides on winning approach to Criteo CTR Prediction competition]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Matters_Columns&diff=43AI Matters Columns2018-09-15T18:17:58Z<p>ToddNeller: /* AI Education Matters */</p>
<hr />
<div>=AI Education Matters=<br />
[https://sigai.acm.org/aimatters/ AI Matters] "AI Education Matters" Columns:<br />
* Vol. 2, Issue 4, Summer 2016: [https://sigai.acm.org/static/aimatters/2-4/AIMatters-2-4-03-Neller.pdf Birds of a Feather] and [[Birds_of_a_Feather|wiki page]].<br />
* Vol. 3, Issue 1, Winter 2017: [https://sigai.acm.org/static/aimatters/3-1/AIMatters-3-1-04-Neller.pdf Open Access AI Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 2, Spring 2017: [https://sigai.acm.org/static/aimatters/3-2/AIMatters-3-2-05-Neller.pdf Machine Learning Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 3, Summer 2017: [https://sigai.acm.org/static/aimatters/3-3/AIMatters-3-3-06-Neller.pdf Deep Neural Network Learning Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 4, Winter 2018: [https://sigai.acm.org/static/aimatters/3-4/AIMatters-3-4-06-Eckroth.pdf Adaptive Planning] and [http://modelai.gettysburg.edu/2017/gitplanner/index.html Git Planner Model AI Assignment project link]<br />
* Vol. 4, Issue 1, Spring 2018: [https://sigai.acm.org/static/aimatters/4-1/AIMatters-4-1-05-Neller.pdf Teaching Hidden Markov Models] and [[Resources]] wiki links<br />
* Vol. 4, Issue 2, Summer 2018: [https://sigai.acm.org/static/aimatters/4-2/AIMatters-4-2-02-Neller.pdf AI Education Matters: Lessons from a Kaggle Click-Through Rate Prediction Competition] and [[Resources]] wiki links<br />
[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Matters_Columns&diff=42AI Matters Columns2018-04-21T00:22:28Z<p>ToddNeller: /* AI Education Matters */ Teaching HMMs</p>
<hr />
<div>=AI Education Matters=<br />
[https://sigai.acm.org/aimatters/ AI Matters] "AI Education Matters" Columns:<br />
* Vol. 2, Issue 4, Summer 2016: [https://sigai.acm.org/static/aimatters/2-4/AIMatters-2-4-03-Neller.pdf Birds of a Feather] and [[Birds_of_a_Feather|wiki page]].<br />
* Vol. 3, Issue 1, Winter 2017: [https://sigai.acm.org/static/aimatters/3-1/AIMatters-3-1-04-Neller.pdf Open Access AI Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 2, Spring 2017: [https://sigai.acm.org/static/aimatters/3-2/AIMatters-3-2-05-Neller.pdf Machine Learning Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 3, Summer 2017: [https://sigai.acm.org/static/aimatters/3-3/AIMatters-3-3-06-Neller.pdf Deep Neural Network Learning Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 4, Winter 2018: [https://sigai.acm.org/static/aimatters/3-4/AIMatters-3-4-06-Eckroth.pdf Adaptive Planning] and [http://modelai.gettysburg.edu/2017/gitplanner/index.html Git Planner Model AI Assignment project link]<br />
* Vol. 4, Issue 1, Spring 2018: [https://sigai.acm.org/static/aimatters/4-1/AIMatters-4-1-05-Neller.pdf Teaching Hidden Markov Models] and [[Resources]] wiki links<br />
[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=41Resources2018-03-02T03:47:54Z<p>ToddNeller: /* Hidden Markov Models */</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
** [http://www.kdnuggets.com/2017/04/10-free-must-read-books-machine-learning-data-science.html KDNuggets "10 Free Must-Read Books for Machine Learning and Data Science"]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
** [https://ml.berkeley.edu/blog/tutorials/ Berkeley student crash course on ML]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]<br />
==Neural Network Learning==<br />
*Textbooks<br />
** [http://www.deeplearningbook.org/ Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville]<br />
** [http://neuralnetworksanddeeplearning.com/ Michael Nielson's Neural Networks and Deep Learning online book.]<br />
*Websites <br />
** [https://www.facebook.com/groups/DeepNetGroup/ Waikit Lau and Arthur Chan's Artificial Intelligence and Deep Learning (AIDL) Facebook group] and [https://www.facebook.com/groups/DeepNetGroup/permalink/385843868475168/ FAQ]<br />
** [http://yerevann.com/a-guide-to-deep-learning/ A Guide to Deep Learning by YerevaNN Labs]<br />
** [http://p.migdal.pl/2017/04/30/teaching-deep-learning.html Piotr Migdał's Learning Deep Learning with Keras]<br />
** [http://aiplaybook.a16z.com/docs/reference/links a16z team's reference links]<br />
** [http://cs231n.github.io/convolutional-networks/ Stanford's CS 231n Convolutional Networks course website]<br />
** various Wikipedia pages concerning [https://en.wikipedia.org/wiki/Artificial_neural_network artificial neural networks]<br />
** [http://playground.tensorflow.org/ TensorFlow Playground]<br />
** [https://distill.pub/2017/momentum/ Why Momentum Really Works]<br />
** [http://lamda.nju.edu.cn/weixs/project/CNNTricks/CNNTricks.html Xiu-Shen Wei's Must Know Tips/Tricks in Deep Neural Networks]<br />
** [https://medium.com/towards-data-science/secret-sauce-behind-the-beauty-of-deep-learning-beginners-guide-to-activation-functions-a8e23a57d046 Medium.com guide: Understanding Activation Functions]<br />
** [https://github.com/williamFalcon/DeepRLHacks John Schulman's Deep RL Hacks (summarized by William Falcon)]<br />
** [https://blog.waya.ai/deep-residual-learning-9610bb62c355 Michael Dietz's Understand Deep Residual Networks]<br />
*Online Courses<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's Machine Learning course] and [https://www.coursera.org/specializations/deep-learning Coursera Deep Learning specialization]<br />
** [https://www.coursera.org/learn/neural-networks Geoffrey Hinton's Neural Networks for Machine Learning course]<br />
** [http://www.dmi.usherb.ca/~larocheh/neural_networks Hugo Larochelle's graduate-level online Neural Network course]<br />
** [https://medium.freecodecamp.org/dive-into-deep-learning-with-these-23-online-courses-bf247d289cc0 David Venturi's list of Deep Learning online courses]<br />
** [http://thegrandjanitor.com/2016/08/15/learning-deep-learning-my-top-five-resource/ Arthur Chan's top 5]<br />
*Software<br />
** [https://www.tensorflow.org/ TensorFlow] and [https://keras.io/ Keras]<br />
** [https://github.com/Microsoft/cntk Microsoft Cognitive Toolkit (CNTK)]<br />
** [https://github.com/Theano/Theano Theano]<br />
** [http://torch.ch/ Torch] and [http://pytorch.org/ PyTorch])<br />
** [http://caffe.berkeleyvision.org/ Caffe]<br />
** [http://mxnet.io/ MXNet]<br />
** [https://deeplearning4j.org/ DeepLearning4J]<br />
** [https://en.wikipedia.org/wiki/Comparison_of_deep_learning_software Comparison of deep learning software] and [https://twitter.com/fchollet/status/852194634470223873 April 2017 popularity metrics]<br />
*Hardware<br />
** [http://timdettmers.com/2017/04/09/which-gpu-for-deep-learning Tim Dettmers' GPU comparison study]<br />
** [https://d4datascience.wordpress.com/2017/05/06/setting-up-a-gpu-based-deep-learning-machine/ Ved's d4datascience blog entry on setting up a GPU-based deep learning machine]<br />
<br />
=Hidden Markov Models=<br />
* Video Introductions<br />
** [https://youtu.be/mNSQ-prhgsw Daphne Koller's 12-minute video "Template Models: Hidden Markov Models - Stanford University"]<br />
** [https://youtu.be/jY2E6ExLxaw Nando de Freitas' 52-minute UBC lecture "undergraduate machine learning 9: Hidden Markov models - HMM"]<br />
* Texts and Articles<br />
** Russell and Norvig, Artificial Intelligence: a modern approach, 3rd ed, sections 15.3, 20.3.3.<br />
** [https://web.stanford.edu/~jurafsky/slp3/9.pdf Speech and Language Processing, 3rd ed, Chapter 9 by Daniel Jurafsky and James H. Martin]<br />
** [http://www.ece.ucsb.edu/Faculty/Rabiner/ece259/Reprints/tutorial%20on%20hmm%20and%20applications.pdf Lawrence Rabiner tutorial "A tutorial on hidden Markov models and selected applications in speech recognition"]<br />
** Christopher Bishop's "Pattern Recognition and Machine Learning", Section 13.2<br />
** [https://stats.stackexchange.com/questions/3294/resources-for-learning-markov-chain-and-hidden-markov-models StackExchange thread "Resources for learning Markov chain and hidden Markov models"]<br />
* Other Resources<br />
** [https://www.udacity.com/course/intro-to-artificial-intelligence--cs271 Udacity's `"Intro to Artificial Intelligence" course by Peter Norvig and Sebastian Thrun]<br />
** [https://www.udacity.com/course/probabalistic-models--cx27 Udacity's "Artificial Intelligence - Probabalistic Models"]<br />
** [https://www.coursera.org/learn/bioinformatics-pku/lecture/7pbUo/hidden-markov-model Coursera's Ge Gao lecture on HMMs]<br />
** [http://cs.jhu.edu/~jason/papers/eisner.hmm.xls Jason Eisner's spreadsheet for teaching the forward-backward algorithm] and [https://cs.jhu.edu/~jason/papers/eisner.tnlp02.pdf his paper on using it for teaching] <br />
** [https://www.quora.com/What-are-some-good-resources-for-learning-about-Hidden-Markov-Models Quora question "What are some good resources for learning about Hidden Markov Models?"]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
** [http://modelai.gettysburg.edu/2017/hmm Sravana Reddy's "Implementing a Hidden Markov Model Toolkit"]<br />
** [http://modelai.gettysburg.edu/2010/pacman/projects/tracking/busters.html John DeNero and Dan Klein's "The Pac-Man Projects" Project #4: Ghostbusters]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=40Resources2018-03-02T03:45:12Z<p>ToddNeller: HMMs</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
** [http://www.kdnuggets.com/2017/04/10-free-must-read-books-machine-learning-data-science.html KDNuggets "10 Free Must-Read Books for Machine Learning and Data Science"]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
** [https://ml.berkeley.edu/blog/tutorials/ Berkeley student crash course on ML]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]<br />
==Neural Network Learning==<br />
*Textbooks<br />
** [http://www.deeplearningbook.org/ Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville]<br />
** [http://neuralnetworksanddeeplearning.com/ Michael Nielson's Neural Networks and Deep Learning online book.]<br />
*Websites <br />
** [https://www.facebook.com/groups/DeepNetGroup/ Waikit Lau and Arthur Chan's Artificial Intelligence and Deep Learning (AIDL) Facebook group] and [https://www.facebook.com/groups/DeepNetGroup/permalink/385843868475168/ FAQ]<br />
** [http://yerevann.com/a-guide-to-deep-learning/ A Guide to Deep Learning by YerevaNN Labs]<br />
** [http://p.migdal.pl/2017/04/30/teaching-deep-learning.html Piotr Migdał's Learning Deep Learning with Keras]<br />
** [http://aiplaybook.a16z.com/docs/reference/links a16z team's reference links]<br />
** [http://cs231n.github.io/convolutional-networks/ Stanford's CS 231n Convolutional Networks course website]<br />
** various Wikipedia pages concerning [https://en.wikipedia.org/wiki/Artificial_neural_network artificial neural networks]<br />
** [http://playground.tensorflow.org/ TensorFlow Playground]<br />
** [https://distill.pub/2017/momentum/ Why Momentum Really Works]<br />
** [http://lamda.nju.edu.cn/weixs/project/CNNTricks/CNNTricks.html Xiu-Shen Wei's Must Know Tips/Tricks in Deep Neural Networks]<br />
** [https://medium.com/towards-data-science/secret-sauce-behind-the-beauty-of-deep-learning-beginners-guide-to-activation-functions-a8e23a57d046 Medium.com guide: Understanding Activation Functions]<br />
** [https://github.com/williamFalcon/DeepRLHacks John Schulman's Deep RL Hacks (summarized by William Falcon)]<br />
** [https://blog.waya.ai/deep-residual-learning-9610bb62c355 Michael Dietz's Understand Deep Residual Networks]<br />
*Online Courses<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's Machine Learning course] and [https://www.coursera.org/specializations/deep-learning Coursera Deep Learning specialization]<br />
** [https://www.coursera.org/learn/neural-networks Geoffrey Hinton's Neural Networks for Machine Learning course]<br />
** [http://www.dmi.usherb.ca/~larocheh/neural_networks Hugo Larochelle's graduate-level online Neural Network course]<br />
** [https://medium.freecodecamp.org/dive-into-deep-learning-with-these-23-online-courses-bf247d289cc0 David Venturi's list of Deep Learning online courses]<br />
** [http://thegrandjanitor.com/2016/08/15/learning-deep-learning-my-top-five-resource/ Arthur Chan's top 5]<br />
*Software<br />
** [https://www.tensorflow.org/ TensorFlow] and [https://keras.io/ Keras]<br />
** [https://github.com/Microsoft/cntk Microsoft Cognitive Toolkit (CNTK)]<br />
** [https://github.com/Theano/Theano Theano]<br />
** [http://torch.ch/ Torch] and [http://pytorch.org/ PyTorch])<br />
** [http://caffe.berkeleyvision.org/ Caffe]<br />
** [http://mxnet.io/ MXNet]<br />
** [https://deeplearning4j.org/ DeepLearning4J]<br />
** [https://en.wikipedia.org/wiki/Comparison_of_deep_learning_software Comparison of deep learning software] and [https://twitter.com/fchollet/status/852194634470223873 April 2017 popularity metrics]<br />
*Hardware<br />
** [http://timdettmers.com/2017/04/09/which-gpu-for-deep-learning Tim Dettmers' GPU comparison study]<br />
** [https://d4datascience.wordpress.com/2017/05/06/setting-up-a-gpu-based-deep-learning-machine/ Ved's d4datascience blog entry on setting up a GPU-based deep learning machine]<br />
<br />
=Hidden Markov Models=<br />
* Video Introductions<br />
** [https://youtu.be/mNSQ-prhgsw Daphne Koller's 12-minute video "Template Models: Hidden Markov Models - Stanford University"]<br />
** [https://youtu.be/jY2E6ExLxaw Nando de Freitas' 52-minute UBC lecture "undergraduate machine learning 9: Hidden Markov models - HMM"]<br />
* Texts and Articles<br />
** Russell and Norvig, Artificial Intelligence: a modern approach, 3rd ed, sections 15.3, 20.3.3.<br />
** [https://web.stanford.edu/~jurafsky/slp3/9.pdf Speech and Language Processing, 3rd ed, Chapter 9 by Daniel Jurafsky and James H. Martin]<br />
** [Lawrence Rabiner tutorial "A tutorial on hidden Markov models and selected applications in speech recognition"]<br />
** Christopher Bishop's "Pattern Recognition and Machine Learning", Section 13.2<br />
** [https://stats.stackexchange.com/questions/3294/resources-for-learning-markov-chain-and-hidden-markov-models StackExchange thread "Resources for learning Markov chain and hidden Markov models"]<br />
* Other Resources<br />
** [https://www.udacity.com/course/intro-to-artificial-intelligence--cs271 Udacity's `"Intro to Artificial Intelligence" course by Peter Norvig and Sebastian Thrun]<br />
** [https://www.udacity.com/course/probabalistic-models--cx27 Udacity's "Artificial Intelligence - Probabalistic Models"]<br />
** [https://www.coursera.org/learn/bioinformatics-pku/lecture/7pbUo/hidden-markov-model Coursera's Ge Gao lecture on HMMs]<br />
** [http://cs.jhu.edu/~jason/papers/eisner.hmm.xls Jason Eisner's spreadsheet for teaching the forward-backward algorithm] and [https://cs.jhu.edu/~jason/papers/eisner.tnlp02.pdf his paper on using it for teaching] <br />
** [https://www.quora.com/What-are-some-good-resources-for-learning-about-Hidden-Markov-Models Quora question "What are some good resources for learning about Hidden Markov Models?"]<br />
* Model AI Assignments<br />
** [http://modelai.gettysburg.edu/2017/hmm Sravana Reddy's "Implementing a Hidden Markov Model Toolkit"]<br />
** [http://modelai.gettysburg.edu/2010/pacman/projects/tracking/busters.html John DeNero and Dan Klein's "The Pac-Man Projects" Project #4: Ghostbusters]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Main_Page&diff=39Main Page2018-03-02T03:07:16Z<p>ToddNeller: /* AI Education */</p>
<hr />
<div>=[[AI Education]]=<br />
*[[AI Matters Columns]] and related wiki pages:<br />
**[[Birds of a Feather]]<br />
**[[Resources]]<br />
*[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Matters_Columns&diff=38AI Matters Columns2018-01-16T15:56:33Z<p>ToddNeller: /* AI Education Matters */</p>
<hr />
<div>=AI Education Matters=<br />
[https://sigai.acm.org/aimatters/ AI Matters] "AI Education Matters" Columns:<br />
* Vol. 2, Issue 4, Summer 2016: [https://sigai.acm.org/static/aimatters/2-4/AIMatters-2-4-03-Neller.pdf Birds of a Feather] and [[Birds_of_a_Feather|wiki page]].<br />
* Vol. 3, Issue 1, Winter 2017: [https://sigai.acm.org/static/aimatters/3-1/AIMatters-3-1-04-Neller.pdf Open Access AI Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 2, Spring 2017: [https://sigai.acm.org/static/aimatters/3-2/AIMatters-3-2-05-Neller.pdf Machine Learning Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 3, Summer 2017: [https://sigai.acm.org/static/aimatters/3-3/AIMatters-3-3-06-Neller.pdf Deep Neural Network Learning Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 4, Winter 2018: [https://sigai.acm.org/static/aimatters/3-4/AIMatters-3-4-06-Eckroth.pdf Adaptive Planning] and [http://modelai.gettysburg.edu/2017/gitplanner/index.html Git Planner Model AI Assignment project link]<br />
[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=37Resources2018-01-05T15:55:49Z<p>ToddNeller: /* Neural Network Learning */</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
** [http://www.kdnuggets.com/2017/04/10-free-must-read-books-machine-learning-data-science.html KDNuggets "10 Free Must-Read Books for Machine Learning and Data Science"]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
** [https://ml.berkeley.edu/blog/tutorials/ Berkeley student crash course on ML]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]<br />
==Neural Network Learning==<br />
*Textbooks<br />
** [http://www.deeplearningbook.org/ Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville]<br />
** [http://neuralnetworksanddeeplearning.com/ Michael Nielson's Neural Networks and Deep Learning online book.]<br />
*Websites <br />
** [https://www.facebook.com/groups/DeepNetGroup/ Waikit Lau and Arthur Chan's Artificial Intelligence and Deep Learning (AIDL) Facebook group] and [https://www.facebook.com/groups/DeepNetGroup/permalink/385843868475168/ FAQ]<br />
** [http://yerevann.com/a-guide-to-deep-learning/ A Guide to Deep Learning by YerevaNN Labs]<br />
** [http://p.migdal.pl/2017/04/30/teaching-deep-learning.html Piotr Migdał's Learning Deep Learning with Keras]<br />
** [http://aiplaybook.a16z.com/docs/reference/links a16z team's reference links]<br />
** [http://cs231n.github.io/convolutional-networks/ Stanford's CS 231n Convolutional Networks course website]<br />
** various Wikipedia pages concerning [https://en.wikipedia.org/wiki/Artificial_neural_network artificial neural networks]<br />
** [http://playground.tensorflow.org/ TensorFlow Playground]<br />
** [https://distill.pub/2017/momentum/ Why Momentum Really Works]<br />
** [http://lamda.nju.edu.cn/weixs/project/CNNTricks/CNNTricks.html Xiu-Shen Wei's Must Know Tips/Tricks in Deep Neural Networks]<br />
** [https://medium.com/towards-data-science/secret-sauce-behind-the-beauty-of-deep-learning-beginners-guide-to-activation-functions-a8e23a57d046 Medium.com guide: Understanding Activation Functions]<br />
** [https://github.com/williamFalcon/DeepRLHacks John Schulman's Deep RL Hacks (summarized by William Falcon)]<br />
** [https://blog.waya.ai/deep-residual-learning-9610bb62c355 Michael Dietz's Understand Deep Residual Networks]<br />
*Online Courses<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's Machine Learning course] and [https://www.coursera.org/specializations/deep-learning Coursera Deep Learning specialization]<br />
** [https://www.coursera.org/learn/neural-networks Geoffrey Hinton's Neural Networks for Machine Learning course]<br />
** [http://www.dmi.usherb.ca/~larocheh/neural_networks Hugo Larochelle's graduate-level online Neural Network course]<br />
** [https://medium.freecodecamp.org/dive-into-deep-learning-with-these-23-online-courses-bf247d289cc0 David Venturi's list of Deep Learning online courses]<br />
** [http://thegrandjanitor.com/2016/08/15/learning-deep-learning-my-top-five-resource/ Arthur Chan's top 5]<br />
*Software<br />
** [https://www.tensorflow.org/ TensorFlow] and [https://keras.io/ Keras]<br />
** [https://github.com/Microsoft/cntk Microsoft Cognitive Toolkit (CNTK)]<br />
** [https://github.com/Theano/Theano Theano]<br />
** [http://torch.ch/ Torch] and [http://pytorch.org/ PyTorch])<br />
** [http://caffe.berkeleyvision.org/ Caffe]<br />
** [http://mxnet.io/ MXNet]<br />
** [https://deeplearning4j.org/ DeepLearning4J]<br />
** [https://en.wikipedia.org/wiki/Comparison_of_deep_learning_software Comparison of deep learning software] and [https://twitter.com/fchollet/status/852194634470223873 April 2017 popularity metrics]<br />
*Hardware<br />
** [http://timdettmers.com/2017/04/09/which-gpu-for-deep-learning Tim Dettmers' GPU comparison study]<br />
** [https://d4datascience.wordpress.com/2017/05/06/setting-up-a-gpu-based-deep-learning-machine/ Ved's d4datascience blog entry on setting up a GPU-based deep learning machine]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Birds_of_a_Feather&diff=36Birds of a Feather2017-12-22T16:59:55Z<p>ToddNeller: /* Birds of a Feather Research */</p>
<hr />
<div>=Birds of a Feather Rules=<br />
<br />
FreeCell stands out among solitaire card games because it is essentially a random self-generating puzzle that has perfect information and can be solved with high probability. Players over the years have, as a community, researched many aspects of the game.[http://solitairelaboratory.com/fcfaq.html]<br />
<br />
Birds of a Feather is an original perfect-information solitaire game played with a standard 52-card deck. After shuffling, the player deals the cards face-up left-to-right in c columns, and top-to-bottom in r rows to create an r-by-c grid of cards.<br />
An example 4-by-4 game's initial layout:<br />
<br />
<nowiki>5S JC QH 8H<br />
KC 6H 3H 9H<br />
3S JS TH TS<br />
KS 7D AH 5C</nowiki><br />
<br />
Think of each grid cell as initially containing a 1-card stack. A stack may be moved on top of another stack in the same row, or in the same column if at least one of two conditions is met: (1) The top card of each stack has the same suit. (2) The top card of each stack has the same rank or an adjacent rank (with Aces low and Kings high and Ace and King non-adjacent). Thus the 9H (9 of Hearts) stack can move onto the TS (Ten of Spades) being adjacent/same in rank:<br />
<br />
<nowiki>5S JC QH 8H <br />
KC 6H 3H <br />
3S JS TH 9H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the 8H stack can move onto the 9H stack being both of (1) same suit and (2) same/adjacent rank:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS TH 8H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the TH stack can move onto the AH stack being of the same suit:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS 8H <br />
KS 7D TH 5C</nowiki><br />
<br />
If we notate each move as the top cards of the moving and destination stacks separated by a hyphen, then this entire tableau can be formed into a single stack from this sequence of moves: <br />
<br />
<nowiki>9H-TS 8H-9H TH-AH 3H-TH QH-3H 6H-7D JC-JS 3S-KS 5S-3S 5C-5S KC-5C QH-KC QH-6H QH-JC QH-8H</nowiki><br />
<br />
Let us call this simple solution concept a "single-stack solution". However, we can define a more general solution concept of forming largest stacks by defining the score of a grid to be the sum of the squares of the stack sizes. The general solution of any grid is a sequence of moves that maximizes this grid score.<br />
<br />
=Birds of a Feather Questions=<br />
<br />
Having defined the puzzle, we can now ask many interesting questions about the game. For r rows and c columns, <br />
*What is the probability that a deal will have a single-stack solution?<br />
*What is the maximal score distribution of deals?<br />
*What are heuristics that can be used to guide search more efficiently to solutions?<br />
*What are characteristics of grids without single-stack solutions?<br />
<br />
There are also many questions one can ask with regard to the automated design of Birds of a Feather puzzles:<br />
*What are the most important attributes of challenging deals with single-stack solutions?<br />
*How can such attributes best combine to form an objective function that can be used to generate Birds of a Feather puzzles through combinatorial optimization algorithms (e.g. simulated annealing)?<br />
<br />
Given this fresh ground for exploration, we would invite educators and students to explore these and other questions concerning Birds of a Feather, and we can summarize our results in a future column.<br />
<br />
The best learning is through experience, and we hope that this grit results in some pearls of work in the months to come. To share your results, please email Todd Neller (tneller@gettysburg.edu) and we invite you to register with and add to our wiki on the subject [[#top|Birds of a Feather]].<br />
<br />
=Birds of a Feather Research=<br />
<br />
We are currently inviting faculty-mentored undergraduate student researchers to research Birds of a Feather questions and publish/present their results at EAAI-2019: The Ninth Symposium on Educational Advanced in Artificial Intelligence. Details can be found [http://cs.gettysburg.edu/~tneller/puzzles/boaf/index.html here].<br />
<br />
Following EAAI-2019, we will summarize what has been learned so far about Birds of a Feather on [http://cs.gettysburg.edu/~tneller/puzzles/boaf/index.html this page].</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Matters_Columns&diff=35AI Matters Columns2017-10-05T19:12:26Z<p>ToddNeller: /* AI Education Matters */</p>
<hr />
<div>=AI Education Matters=<br />
[https://sigai.acm.org/aimatters/ AI Matters] "AI Education Matters" Columns:<br />
* Vol. 2, Issue 4, Summer 2016: [https://sigai.acm.org/static/aimatters/2-4/AIMatters-2-4-03-Neller.pdf Birds of a Feather] and [[Birds_of_a_Feather|wiki page]].<br />
* Vol. 3, Issue 1, Winter 2017: [https://sigai.acm.org/static/aimatters/3-1/AIMatters-3-1-04-Neller.pdf Open Access AI Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 2, Spring 2017: [https://sigai.acm.org/static/aimatters/3-2/AIMatters-3-2-05-Neller.pdf Machine Learning Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 3, Summer 2017: [https://sigai.acm.org/static/aimatters/3-3/AIMatters-3-3-06-Neller.pdf Deep Neural Network Learning Resources] and [[Resources]] wiki links.<br />
[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Matters_Columns&diff=34AI Matters Columns2017-09-15T15:17:22Z<p>ToddNeller: addition of latest issues</p>
<hr />
<div>=AI Education Matters=<br />
[https://sigai.acm.org/aimatters/ AI Matters] "AI Education Matters" Columns:<br />
* Vol. 2, Issue 4, Summer 2016: [https://sigai.acm.org/static/aimatters/2-4/AIMatters-2-4-03-Neller.pdf Birds of a Feather] and [[Birds_of_a_Feather|wiki page]].<br />
* Vol. 3, Issue 1, Winter 2017: [https://sigai.acm.org/static/aimatters/3-1/AIMatters-3-1-04-Neller.pdf Open Access AI Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 2, Spring 2017: [https://sigai.acm.org/static/aimatters/3-2/AIMatters-3-2-05-Neller.pdf Machine Learning Resources] and [[Resources]] wiki links.<br />
* Vol. 3, Issue 3, Summer 2017: [https://sigai.acm.org/static/aimatters/3-3/AIMatters-3-3-06-Neller.pdf Deep Neural Network Learning Resources] and [[Resources]] wiki links..<br />
[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=33Resources2017-09-13T15:45:54Z<p>ToddNeller: /* Machine Learning */ adding kdnuggets link</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
** [http://www.kdnuggets.com/2017/04/10-free-must-read-books-machine-learning-data-science.html KDNuggets "10 Free Must-Read Books for Machine Learning and Data Science"]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
** [https://ml.berkeley.edu/blog/tutorials/ Berkeley student crash course on ML]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]<br />
==Neural Network Learning==<br />
*Textbooks<br />
** [http://www.deeplearningbook.org/ Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville]<br />
** [http://neuralnetworksanddeeplearning.com/ Michael Nielson's Neural Networks and Deep Learning online book.]<br />
*Websites <br />
** [https://www.facebook.com/groups/DeepNetGroup/ Waikit Lau and Arthur Chan's Artificial Intelligence and Deep Learning (AIDL) Facebook group] and [https://www.facebook.com/groups/DeepNetGroup/permalink/385843868475168/ FAQ]<br />
** [http://yerevann.com/a-guide-to-deep-learning/ A Guide to Deep Learning by YerevaNN Labs]<br />
** [http://p.migdal.pl/2017/04/30/teaching-deep-learning.html Piotr Migdał's Learning Deep Learning with Keras]<br />
** [http://aiplaybook.a16z.com/docs/reference/links a16z team's reference links]<br />
** [http://cs231n.github.io/convolutional-networks/ Stanford's CS 231n Convolutional Networks course website]<br />
** various Wikipedia pages concerning [https://en.wikipedia.org/wiki/Artificial_neural_network artificial neural networks]<br />
** [http://playground.tensorflow.org/ TensorFlow Playground]<br />
** [https://distill.pub/2017/momentum/ Why Momentum Really Works]<br />
** [http://lamda.nju.edu.cn/weixs/project/CNNTricks/CNNTricks.html Xiu-Shen Wei's Must Know Tips/Tricks in Deep Neural Networks]<br />
** [https://medium.com/towards-data-science/secret-sauce-behind-the-beauty-of-deep-learning-beginners-guide-to-activation-functions-a8e23a57d046 Medium.com guide: Understanding Activation Functions]<br />
** [https://github.com/williamFalcon/DeepRLHacks John Schulman's Deep RL Hacks (summarized by William Falcon)]<br />
*Online Courses<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's Machine Learning course] and [https://www.coursera.org/specializations/deep-learning Coursera Deep Learning specialization]<br />
** [https://www.coursera.org/learn/neural-networks Geoffrey Hinton's Neural Networks for Machine Learning course]<br />
** [http://www.dmi.usherb.ca/~larocheh/neural_networks Hugo Larochelle's graduate-level online Neural Network course]<br />
** [https://medium.freecodecamp.org/dive-into-deep-learning-with-these-23-online-courses-bf247d289cc0 David Venturi's list of Deep Learning online courses]<br />
** [http://thegrandjanitor.com/2016/08/15/learning-deep-learning-my-top-five-resource/ Arthur Chan's top 5]<br />
*Software<br />
** [https://www.tensorflow.org/ TensorFlow] and [https://keras.io/ Keras]<br />
** [https://github.com/Microsoft/cntk Microsoft Cognitive Toolkit (CNTK)]<br />
** [https://github.com/Theano/Theano Theano]<br />
** [http://torch.ch/ Torch] and [http://pytorch.org/ PyTorch])<br />
** [http://caffe.berkeleyvision.org/ Caffe]<br />
** [http://mxnet.io/ MXNet]<br />
** [https://deeplearning4j.org/ DeepLearning4J]<br />
** [https://en.wikipedia.org/wiki/Comparison_of_deep_learning_software Comparison of deep learning software] and [https://twitter.com/fchollet/status/852194634470223873 April 2017 popularity metrics]<br />
*Hardware<br />
** [http://timdettmers.com/2017/04/09/which-gpu-for-deep-learning Tim Dettmers' GPU comparison study]<br />
** [https://d4datascience.wordpress.com/2017/05/06/setting-up-a-gpu-based-deep-learning-machine/ Ved's d4datascience blog entry on setting up a GPU-based deep learning machine]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=32Resources2017-08-30T14:39:42Z<p>ToddNeller: /* Neural Network Learning */ adding links</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
** [https://ml.berkeley.edu/blog/tutorials/ Berkeley student crash course on ML]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]<br />
==Neural Network Learning==<br />
*Textbooks<br />
** [http://www.deeplearningbook.org/ Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville]<br />
** [http://neuralnetworksanddeeplearning.com/ Michael Nielson's Neural Networks and Deep Learning online book.]<br />
*Websites <br />
** [https://www.facebook.com/groups/DeepNetGroup/ Waikit Lau and Arthur Chan's Artificial Intelligence and Deep Learning (AIDL) Facebook group] and [https://www.facebook.com/groups/DeepNetGroup/permalink/385843868475168/ FAQ]<br />
** [http://yerevann.com/a-guide-to-deep-learning/ A Guide to Deep Learning by YerevaNN Labs]<br />
** [http://p.migdal.pl/2017/04/30/teaching-deep-learning.html Piotr Migdał's Learning Deep Learning with Keras]<br />
** [http://aiplaybook.a16z.com/docs/reference/links a16z team's reference links]<br />
** [http://cs231n.github.io/convolutional-networks/ Stanford's CS 231n Convolutional Networks course website]<br />
** various Wikipedia pages concerning [https://en.wikipedia.org/wiki/Artificial_neural_network artificial neural networks]<br />
** [http://playground.tensorflow.org/ TensorFlow Playground]<br />
** [https://distill.pub/2017/momentum/ Why Momentum Really Works]<br />
** [http://lamda.nju.edu.cn/weixs/project/CNNTricks/CNNTricks.html Xiu-Shen Wei's Must Know Tips/Tricks in Deep Neural Networks]<br />
** [https://medium.com/towards-data-science/secret-sauce-behind-the-beauty-of-deep-learning-beginners-guide-to-activation-functions-a8e23a57d046 Medium.com guide: Understanding Activation Functions]<br />
** [https://github.com/williamFalcon/DeepRLHacks John Schulman's Deep RL Hacks (summarized by William Falcon)]<br />
*Online Courses<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's Machine Learning course] and [https://www.coursera.org/specializations/deep-learning Coursera Deep Learning specialization]<br />
** [https://www.coursera.org/learn/neural-networks Geoffrey Hinton's Neural Networks for Machine Learning course]<br />
** [http://www.dmi.usherb.ca/~larocheh/neural_networks Hugo Larochelle's graduate-level online Neural Network course]<br />
** [https://medium.freecodecamp.org/dive-into-deep-learning-with-these-23-online-courses-bf247d289cc0 David Venturi's list of Deep Learning online courses]<br />
** [http://thegrandjanitor.com/2016/08/15/learning-deep-learning-my-top-five-resource/ Arthur Chan's top 5]<br />
*Software<br />
** [https://www.tensorflow.org/ TensorFlow] and [https://keras.io/ Keras]<br />
** [https://github.com/Microsoft/cntk Microsoft Cognitive Toolkit (CNTK)]<br />
** [https://github.com/Theano/Theano Theano]<br />
** [http://torch.ch/ Torch] and [http://pytorch.org/ PyTorch])<br />
** [http://caffe.berkeleyvision.org/ Caffe]<br />
** [http://mxnet.io/ MXNet]<br />
** [https://deeplearning4j.org/ DeepLearning4J]<br />
** [https://en.wikipedia.org/wiki/Comparison_of_deep_learning_software Comparison of deep learning software] and [https://twitter.com/fchollet/status/852194634470223873 April 2017 popularity metrics]<br />
*Hardware<br />
** [http://timdettmers.com/2017/04/09/which-gpu-for-deep-learning Tim Dettmers' GPU comparison study]<br />
** [https://d4datascience.wordpress.com/2017/05/06/setting-up-a-gpu-based-deep-learning-machine/ Ved's d4datascience blog entry on setting up a GPU-based deep learning machine]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=31Resources2017-08-23T14:26:56Z<p>ToddNeller: /* Neural Network Learning */ adding links</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
** [https://ml.berkeley.edu/blog/tutorials/ Berkeley student crash course on ML]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]<br />
==Neural Network Learning==<br />
*Textbooks<br />
** [http://www.deeplearningbook.org/ Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville]<br />
** [http://neuralnetworksanddeeplearning.com/ Michael Nielson's Neural Networks and Deep Learning online book.]<br />
*Websites <br />
** [https://www.facebook.com/groups/DeepNetGroup/ Waikit Lau and Arthur Chan's Artificial Intelligence and Deep Learning (AIDL) Facebook group] and [https://www.facebook.com/groups/DeepNetGroup/permalink/385843868475168/ FAQ]<br />
** [http://yerevann.com/a-guide-to-deep-learning/ A Guide to Deep Learning by YerevaNN Labs]<br />
** [http://p.migdal.pl/2017/04/30/teaching-deep-learning.html Piotr Migdał's Learning Deep Learning with Keras]<br />
** [http://aiplaybook.a16z.com/docs/reference/links a16z team's reference links]<br />
** [http://cs231n.github.io/convolutional-networks/ Stanford's CS 231n Convolutional Networks course website]<br />
** various Wikipedia pages concerning [https://en.wikipedia.org/wiki/Artificial_neural_network artificial neural networks]<br />
** [http://playground.tensorflow.org/ TensorFlow Playground]<br />
** [https://distill.pub/2017/momentum/ Why Momentum Really Works]<br />
*Online Courses<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's Machine Learning course] and [https://www.coursera.org/specializations/deep-learning Coursera Deep Learning specialization]<br />
** [https://www.coursera.org/learn/neural-networks Geoffrey Hinton's Neural Networks for Machine Learning course]<br />
** [http://www.dmi.usherb.ca/~larocheh/neural_networks Hugo Larochelle's graduate-level online Neural Network course]<br />
** [https://medium.freecodecamp.org/dive-into-deep-learning-with-these-23-online-courses-bf247d289cc0 David Venturi's list of Deep Learning online courses]<br />
** [http://thegrandjanitor.com/2016/08/15/learning-deep-learning-my-top-five-resource/ Arthur Chan's top 5]<br />
*Software<br />
** [https://www.tensorflow.org/ TensorFlow] and [https://keras.io/ Keras]<br />
** [https://github.com/Microsoft/cntk Microsoft Cognitive Toolkit (CNTK)]<br />
** [https://github.com/Theano/Theano Theano]<br />
** [http://torch.ch/ Torch] and [http://pytorch.org/ PyTorch])<br />
** [http://caffe.berkeleyvision.org/ Caffe]<br />
** [http://mxnet.io/ MXNet]<br />
** [https://deeplearning4j.org/ DeepLearning4J]<br />
** [https://en.wikipedia.org/wiki/Comparison_of_deep_learning_software Comparison of deep learning software] and [https://twitter.com/fchollet/status/852194634470223873 April 2017 popularity metrics]<br />
*Hardware<br />
** [http://timdettmers.com/2017/04/09/which-gpu-for-deep-learning Tim Dettmers' GPU comparison study]<br />
** [https://d4datascience.wordpress.com/2017/05/06/setting-up-a-gpu-based-deep-learning-machine/ Ved's d4datascience blog entry on setting up a GPU-based deep learning machine]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=30Resources2017-08-09T19:09:37Z<p>ToddNeller: /* Neural Network Learning */ added Coursera specialization</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
** [https://ml.berkeley.edu/blog/tutorials/ Berkeley student crash course on ML]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]<br />
==Neural Network Learning==<br />
*Textbooks<br />
** [http://www.deeplearningbook.org/ Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville]<br />
** [http://neuralnetworksanddeeplearning.com/ Michael Nielson's Neural Networks and Deep Learning online book.]<br />
*Websites <br />
** [https://www.facebook.com/groups/DeepNetGroup/ Waikit Lau and Arthur Chan's Artificial Intelligence and Deep Learning (AIDL) Facebook group] and [https://www.facebook.com/groups/DeepNetGroup/permalink/385843868475168/ FAQ]<br />
** [http://yerevann.com/a-guide-to-deep-learning/ A Guide to Deep Learning by YerevaNN Labs]<br />
** [http://p.migdal.pl/2017/04/30/teaching-deep-learning.html Piotr Migdał's Learning Deep Learning with Keras]<br />
** [http://aiplaybook.a16z.com/docs/reference/links a16z team's reference links]<br />
** [http://cs231n.github.io/convolutional-networks/ Stanford's CS 231n Convolutional Networks course website]<br />
** various Wikipedia pages concerning [https://en.wikipedia.org/wiki/Artificial_neural_network artificial neural networks]<br />
*Online Courses<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's Machine Learning course] and [https://www.coursera.org/specializations/deep-learning Coursera Deep Learning specialization]<br />
** [https://www.coursera.org/learn/neural-networks Geoffrey Hinton's Neural Networks for Machine Learning course]<br />
** [http://www.dmi.usherb.ca/~larocheh/neural_networks Hugo Larochelle's graduate-level online Neural Network course]<br />
** [https://medium.freecodecamp.org/dive-into-deep-learning-with-these-23-online-courses-bf247d289cc0 David Venturi's list of Deep Learning online courses]<br />
** [http://thegrandjanitor.com/2016/08/15/learning-deep-learning-my-top-five-resource/ Arthur Chan's top 5]<br />
*Software<br />
** [https://www.tensorflow.org/ TensorFlow] and [https://keras.io/ Keras]<br />
** [https://github.com/Microsoft/cntk Microsoft Cognitive Toolkit (CNTK)]<br />
** [https://github.com/Theano/Theano Theano]<br />
** [http://torch.ch/ Torch] and [http://pytorch.org/ PyTorch])<br />
** [http://caffe.berkeleyvision.org/ Caffe]<br />
** [http://mxnet.io/ MXNet]<br />
** [https://deeplearning4j.org/ DeepLearning4J]<br />
** [https://en.wikipedia.org/wiki/Comparison_of_deep_learning_software Comparison of deep learning software] and [https://twitter.com/fchollet/status/852194634470223873 April 2017 popularity metrics]<br />
*Hardware<br />
** [http://timdettmers.com/2017/04/09/which-gpu-for-deep-learning Tim Dettmers' GPU comparison study]<br />
** [https://d4datascience.wordpress.com/2017/05/06/setting-up-a-gpu-based-deep-learning-machine/ Ved's d4datascience blog entry on setting up a GPU-based deep learning machine]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=29Resources2017-07-24T20:10:17Z<p>ToddNeller: /* Machine Learning */ addition</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
** [https://ml.berkeley.edu/blog/tutorials/ Berkeley student crash course on ML]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]<br />
==Neural Network Learning==<br />
*Textbooks<br />
** [http://www.deeplearningbook.org/ Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville]<br />
** [http://neuralnetworksanddeeplearning.com/ Michael Nielson's Neural Networks and Deep Learning online book.]<br />
*Websites <br />
** [https://www.facebook.com/groups/DeepNetGroup/ Waikit Lau and Arthur Chan's Artificial Intelligence and Deep Learning (AIDL) Facebook group] and [https://www.facebook.com/groups/DeepNetGroup/permalink/385843868475168/ FAQ]<br />
** [http://yerevann.com/a-guide-to-deep-learning/ A Guide to Deep Learning by YerevaNN Labs]<br />
** [http://p.migdal.pl/2017/04/30/teaching-deep-learning.html Piotr Migdał's Learning Deep Learning with Keras]<br />
** [http://aiplaybook.a16z.com/docs/reference/links a16z team's reference links]<br />
** [http://cs231n.github.io/convolutional-networks/ Stanford's CS 231n Convolutional Networks course website]<br />
** various Wikipedia pages concerning [https://en.wikipedia.org/wiki/Artificial_neural_network artificial neural networks]<br />
*Online Courses<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's Machine Learning course]<br />
** [https://www.coursera.org/learn/neural-networks Geoffrey Hinton's Neural Networks for Machine Learning course]<br />
** [http://www.dmi.usherb.ca/~larocheh/neural_networks Hugo Larochelle's graduate-level online Neural Network course]<br />
** [https://medium.freecodecamp.org/dive-into-deep-learning-with-these-23-online-courses-bf247d289cc0 David Venturi's list of Deep Learning online courses]<br />
** [http://thegrandjanitor.com/2016/08/15/learning-deep-learning-my-top-five-resource/ Arthur Chan's top 5]<br />
*Software<br />
** [https://www.tensorflow.org/ TensorFlow] and [https://keras.io/ Keras]<br />
** [https://github.com/Microsoft/cntk Microsoft Cognitive Toolkit (CNTK)]<br />
** [https://github.com/Theano/Theano Theano]<br />
** [http://torch.ch/ Torch] and [http://pytorch.org/ PyTorch])<br />
** [http://caffe.berkeleyvision.org/ Caffe]<br />
** [http://mxnet.io/ MXNet]<br />
** [https://deeplearning4j.org/ DeepLearning4J]<br />
** [https://en.wikipedia.org/wiki/Comparison_of_deep_learning_software Comparison of deep learning software] and [https://twitter.com/fchollet/status/852194634470223873 April 2017 popularity metrics]<br />
*Hardware<br />
** [http://timdettmers.com/2017/04/09/which-gpu-for-deep-learning Tim Dettmers' GPU comparison study]<br />
** [https://d4datascience.wordpress.com/2017/05/06/setting-up-a-gpu-based-deep-learning-machine/ Ved's d4datascience blog entry on setting up a GPU-based deep learning machine]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=28Resources2017-07-24T20:07:42Z<p>ToddNeller: Added NN resources</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]<br />
==Neural Network Learning==<br />
*Textbooks<br />
** [http://www.deeplearningbook.org/ Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville]<br />
** [http://neuralnetworksanddeeplearning.com/ Michael Nielson's Neural Networks and Deep Learning online book.]<br />
*Websites <br />
** [https://www.facebook.com/groups/DeepNetGroup/ Waikit Lau and Arthur Chan's Artificial Intelligence and Deep Learning (AIDL) Facebook group] and [https://www.facebook.com/groups/DeepNetGroup/permalink/385843868475168/ FAQ]<br />
** [http://yerevann.com/a-guide-to-deep-learning/ A Guide to Deep Learning by YerevaNN Labs]<br />
** [http://p.migdal.pl/2017/04/30/teaching-deep-learning.html Piotr Migdał's Learning Deep Learning with Keras]<br />
** [http://aiplaybook.a16z.com/docs/reference/links a16z team's reference links]<br />
** [http://cs231n.github.io/convolutional-networks/ Stanford's CS 231n Convolutional Networks course website]<br />
** various Wikipedia pages concerning [https://en.wikipedia.org/wiki/Artificial_neural_network artificial neural networks]<br />
*Online Courses<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's Machine Learning course]<br />
** [https://www.coursera.org/learn/neural-networks Geoffrey Hinton's Neural Networks for Machine Learning course]<br />
** [http://www.dmi.usherb.ca/~larocheh/neural_networks Hugo Larochelle's graduate-level online Neural Network course]<br />
** [https://medium.freecodecamp.org/dive-into-deep-learning-with-these-23-online-courses-bf247d289cc0 David Venturi's list of Deep Learning online courses]<br />
** [http://thegrandjanitor.com/2016/08/15/learning-deep-learning-my-top-five-resource/ Arthur Chan's top 5]<br />
*Software<br />
** [https://www.tensorflow.org/ TensorFlow] and [https://keras.io/ Keras]<br />
** [https://github.com/Microsoft/cntk Microsoft Cognitive Toolkit (CNTK)]<br />
** [https://github.com/Theano/Theano Theano]<br />
** [http://torch.ch/ Torch] and [http://pytorch.org/ PyTorch])<br />
** [http://caffe.berkeleyvision.org/ Caffe]<br />
** [http://mxnet.io/ MXNet]<br />
** [https://deeplearning4j.org/ DeepLearning4J]<br />
** [https://en.wikipedia.org/wiki/Comparison_of_deep_learning_software Comparison of deep learning software] and [https://twitter.com/fchollet/status/852194634470223873 April 2017 popularity metrics]<br />
*Hardware<br />
** [http://timdettmers.com/2017/04/09/which-gpu-for-deep-learning Tim Dettmers' GPU comparison study]<br />
** [https://d4datascience.wordpress.com/2017/05/06/setting-up-a-gpu-based-deep-learning-machine/ Ved's d4datascience blog entry on setting up a GPU-based deep learning machine]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=27Resources2017-05-22T21:33:52Z<p>ToddNeller: /* Neural Network Learning */</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]<br />
==Neural Network Learning==<br />
*Textbooks<br />
** Neural network basics<br />
***<br />
** Deep learning<br />
***<br />
*Websites <br />
**<br />
*Software<br />
**<br />
*Hardware<br />
**</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=26Resources2017-05-22T16:43:34Z<p>ToddNeller: /* Machine Learning */ created NN subsection</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]<br />
==Neural Network Learning==</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=25Resources2017-04-01T16:07:10Z<p>ToddNeller: Addition of Machine Learning resources</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]<br />
<br />
=General=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1671238 Stuart Russell, Peter Norvig. Artificial Intelligence: a modern approach] <br />
<br />
=Machine Learning=<br />
* Texts:<br />
** [http://dl.acm.org/citation.cfm?id=1162264 Christopher Bishop. Pattern Recognition and Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=2380985 Kevin Murphy. Machine Learning: A Probabilistic Perspective]<br />
** [http://dl.acm.org/citation.cfm?id=2207809 David Barber. Probabilistic Reasoning and Machine Learning] ([http://web4.cs.ucl.ac.uk/staff/D.Barber/textbook/090310.pdf Barber's free PDF version])<br />
** [http://dl.acm.org/citation.cfm?id=541177 Tom Mitchell. Machine Learning]<br />
** [http://dl.acm.org/citation.cfm?id=1734076 Ethem Alpaydin. Introduction to Machine Learning]<br />
** Statistical Learning:<br />
*** [https://statweb.stanford.edu/~tibs/ElemStatLearn/ Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning]<br />
*** [http://www-bcf.usc.edu/~gareth/ISL/ Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani. An Introduction to Statistical Learning with Applications in R] ([https://www.rstudio.com/products/rstudio/ RStudio software for labs])<br />
** Reinforcement Learning:<br />
*** [http://incompleteideas.net/sutton/book/the-book.html Richard Sutton and Andrew Barto. Reinforcement Learning: an introduction] <br />
*** [https://sites.ualberta.ca/~szepesva/RLBook.html Csaba Szepesvári. Algorithms for Reinforcement Learning]<br />
*** [http://dl.acm.org/citation.cfm?id=2670001 Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State-of-the-Art]<br />
* Online resources:<br />
** [https://www.coursera.org/learn/machine-learning Andrew Ng's free online Coursera Machine Learning course]<br />
** [http://archive.ics.uci.edu/ml/ UC Irvine Machine Learning Repository]<br />
** [https://www.kaggle.com/datasets Kaggle datasets]<br />
** [https://www.rstudio.com/products/rstudio/ RStudio software for labs]<br />
** [http://www.cs.waikato.ac.nz/ml/weka/ Weka Java-based Data Mining software] and [http://dl.acm.org/citation.cfm?id=1205860 Ian Witten and Eibe Frank. Data Mining: Practical Machine Learning Tools and Techniques]<br />
** [http://modelai.gettysburg.edu/ Model AI Assignments]<br />
* Recommendations:<br />
** [https://www.quora.com/How-do-I-learn-machine-learning-1 Quora "How do I learn machine learning?" answers]<br />
** [https://github.com/josephmisiti/awesome-machine-learning/blob/master/books.md Joseph Misiti's Machine Learning book recommendations]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Main_Page&diff=24Main Page2017-03-31T19:43:29Z<p>ToddNeller: </p>
<hr />
<div>=[[AI Education]]=<br />
*[[AI Matters Columns]] and related wiki pages:<br />
**[[Birds of a Feather]]<br />
**[[Resources]]<br />
**[[Resources|Machine Learning Resources]]<br />
*[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Resources&diff=23Resources2016-11-14T23:23:41Z<p>ToddNeller: starting places</p>
<hr />
<div>=Starting Places=<br />
* [http://aitopics.org AITopics.org]<br />
* [http://eaai.stanford.edu Educational Advances in AI (EAAI)]<br />
* [http://modelai.gettysburg.edu Model AI Assignments]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Main_Page&diff=22Main Page2016-11-14T23:21:09Z<p>ToddNeller: add resources link</p>
<hr />
<div>=[[AI Education]]=<br />
*[[AI Matters Columns]] and related wiki pages:<br />
**[[Birds of a Feather]]<br />
**[[Resources]]<br />
*[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Main_Page&diff=21Main Page2016-11-09T16:48:56Z<p>ToddNeller: </p>
<hr />
<div>=[[AI Education]]=<br />
*[[AI Matters Columns]] and related wiki pages:<br />
**[[Birds of a Feather]]<br />
*[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Ed_Column_Ideas&diff=20AI Ed Column Ideas2016-11-09T16:45:38Z<p>ToddNeller: </p>
<hr />
<div>*AI Ed Resources Introduction <br />
*AI Ed MOOCs<br />
*AI Ed Competitions<br />
*Undergraduate Research Challenge Problems - The creation and sharing of challenge problems aid the AI educator in that (1) the best education is through experience, and (2) novel challenge problems provide unique experiences, questions, and answers that cannot simply be searched online. <br />
*Model AI Assignment Highlights - highlight Model AI Assignment work to encourage instructors to take advantage of the resources found on the [http://modelai.gettysburg.edu Model AI Assignments website].</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Matters_Columns&diff=19AI Matters Columns2016-11-09T16:41:51Z<p>ToddNeller: </p>
<hr />
<div>=AI Education Matters=<br />
* Vol. 2, Issue 4, Summer 2016: [https://sigai.acm.org/static/aimatters/2-4/AIMatters-2-4-03-Neller.pdf Birds of a Feather] and [[Birds_of_a_Feather|wiki page]].<br />
<br />
[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Matters_Columns&diff=18AI Matters Columns2016-11-09T16:41:18Z<p>ToddNeller: /* AI Education Matters */</p>
<hr />
<div>=AI Matters Columns=<br />
<br />
== AI Education Matters ==<br />
* Vol. 2, Issue 4, Summer 2016: [https://sigai.acm.org/static/aimatters/2-4/AIMatters-2-4-03-Neller.pdf Birds of a Feather] and [[Birds_of_a_Feather|wiki page]].<br />
<br />
[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Matters_Columns&diff=17AI Matters Columns2016-11-09T16:40:34Z<p>ToddNeller: page creation</p>
<hr />
<div>=AI Matters Columns=<br />
<br />
== AI Education Matters ==<br />
* Vol. 2, No. 4: [https://sigai.acm.org/static/aimatters/2-4/AIMatters-2-4-03-Neller.pdf Birds of a Feather] and [[Birds_of_a_Feather|wiki page]].<br />
<br />
[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Education&diff=16AI Education2016-11-09T16:36:46Z<p>ToddNeller: </p>
<hr />
<div>[[AI Matters Columns]]<br />
<br />
[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Education&diff=15AI Education2016-11-09T16:36:34Z<p>ToddNeller: </p>
<hr />
<div>[[AI Matters Columns]]<br />
[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Birds_of_a_Feather&diff=14Birds of a Feather2016-09-27T20:50:15Z<p>ToddNeller: Add section for future research additions</p>
<hr />
<div>=Birds of a Feather Rules=<br />
<br />
FreeCell stands out among solitaire card games because it is essentially a random self-generating puzzle that has perfect information and can be solved with high probability. Players over the years have, as a community, researched many aspects of the game.[http://solitairelaboratory.com/fcfaq.html]<br />
<br />
Birds of a Feather is an original perfect-information solitaire game played with a standard 52-card deck. After shuffling, the player deals the cards face-up left-to-right in c columns, and top-to-bottom in r rows to create an r-by-c grid of cards.<br />
An example 4-by-4 game's initial layout:<br />
<br />
<nowiki>5S JC QH 8H<br />
KC 6H 3H 9H<br />
3S JS TH TS<br />
KS 7D AH 5C</nowiki><br />
<br />
Think of each grid cell as initially containing a 1-card stack. A stack may be moved on top of another stack in the same row, or in the same column if at least one of two conditions is met: (1) The top card of each stack has the same suit. (2) The top card of each stack has the same rank or an adjacent rank (with Aces low and Kings high and Ace and King non-adjacent). Thus the 9H (9 of Hearts) stack can move onto the TS (Ten of Spades) being adjacent/same in rank:<br />
<br />
<nowiki>5S JC QH 8H <br />
KC 6H 3H <br />
3S JS TH 9H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the 8H stack can move onto the 9H stack being both of (1) same suit and (2) same/adjacent rank:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS TH 8H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the TH stack can move onto the AH stack being of the same suit:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS 8H <br />
KS 7D TH 5C</nowiki><br />
<br />
If we notate each move as the top cards of the moving and destination stacks separated by a hyphen, then this entire tableau can be formed into a single stack from this sequence of moves: <br />
<br />
<nowiki>9H-TS 8H-9H TH-AH 3H-TH QH-3H 6H-7D JC-JS 3S-KS 5S-3S 5C-5S KC-5C QH-KC QH-6H QH-JC QH-8H</nowiki><br />
<br />
Let us call this simple solution concept a "single-stack solution". However, we can define a more general solution concept of forming largest stacks by defining the score of a grid to be the sum of the squares of the stack sizes. The general solution of any grid is a sequence of moves that maximizes this grid score.<br />
<br />
=Birds of a Feather Questions=<br />
<br />
Having defined the puzzle, we can now ask many interesting questions about the game. For r rows and c columns, <br />
*What is the probability that a deal will have a single-stack solution?<br />
*What is the maximal score distribution of deals?<br />
*What are heuristics that can be used to guide search more efficiently to solutions?<br />
*What are characteristics of grids without single-stack solutions?<br />
<br />
There are also many questions one can ask with regard to the automated design of Birds of a Feather puzzles:<br />
*What are the most important attributes of challenging deals with single-stack solutions?<br />
*How can such attributes best combine to form an objective function that can be used to generate Birds of a Feather puzzles through combinatorial optimization algorithms (e.g. simulated annealing)?<br />
<br />
Given this fresh ground for exploration, we would invite educators and students to explore these and other questions concerning Birds of a Feather, and we can summarize our results in a future column.<br />
<br />
The best learning is through experience, and we hope that this grit results in some pearls of work in the months to come. To share your results, please email Todd Neller (tneller@gettysburg.edu) and we invite you to register with and add to our wiki on the subject [[#top|Birds of a Feather]].<br />
<br />
=Birds of a Feather Research=<br />
<br />
In this section, we summarize what has been learned so far about Birds of a Feather.</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Birds_of_a_Feather&diff=13Birds of a Feather2016-09-27T20:40:36Z<p>ToddNeller: Update game name</p>
<hr />
<div>=Birds of a Feather Rules=<br />
<br />
FreeCell stands out among solitaire card games because it is essentially a random self-generating puzzle that has perfect information and can be solved with high probability. Players over the years have, as a community, researched many aspects of the game.[http://solitairelaboratory.com/fcfaq.html]<br />
<br />
Birds of a Feather is an original perfect-information solitaire game played with a standard 52-card deck. After shuffling, the player deals the cards face-up left-to-right in c columns, and top-to-bottom in r rows to create an r-by-c grid of cards.<br />
An example 4-by-4 game's initial layout:<br />
<br />
<nowiki>5S JC QH 8H<br />
KC 6H 3H 9H<br />
3S JS TH TS<br />
KS 7D AH 5C</nowiki><br />
<br />
Think of each grid cell as initially containing a 1-card stack. A stack may be moved on top of another stack in the same row, or in the same column if at least one of two conditions is met: (1) The top card of each stack has the same suit. (2) The top card of each stack has the same rank or an adjacent rank (with Aces low and Kings high and Ace and King non-adjacent). Thus the 9H (9 of Hearts) stack can move onto the TS (Ten of Spades) being adjacent/same in rank:<br />
<br />
<nowiki>5S JC QH 8H <br />
KC 6H 3H <br />
3S JS TH 9H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the 8H stack can move onto the 9H stack being both of (1) same suit and (2) same/adjacent rank:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS TH 8H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the TH stack can move onto the AH stack being of the same suit:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS 8H <br />
KS 7D TH 5C</nowiki><br />
<br />
If we notate each move as the top cards of the moving and destination stacks separated by a hyphen, then this entire tableau can be formed into a single stack from this sequence of moves: <br />
<br />
<nowiki>9H-TS 8H-9H TH-AH 3H-TH QH-3H 6H-7D JC-JS 3S-KS 5S-3S 5C-5S KC-5C QH-KC QH-6H QH-JC QH-8H</nowiki><br />
<br />
Let us call this simple solution concept a "single-stack solution". However, we can define a more general solution concept of forming largest stacks by defining the score of a grid to be the sum of the squares of the stack sizes. The general solution of any grid is a sequence of moves that maximizes this grid score.<br />
<br />
=Birds of a Feather Questions=<br />
<br />
Having defined the puzzle, we can now ask many interesting questions about the game. For r rows and c columns, <br />
*What is the probability that a deal will have a single-stack solution?<br />
*What is the maximal score distribution of deals?<br />
*What are heuristics that can be used to guide search more efficiently to solutions?<br />
*What are characteristics of grids without single-stack solutions?<br />
<br />
There are also many questions one can ask with regard to the automated design of Birds of a Feather puzzles:<br />
*What are the most important attributes of challenging deals with single-stack solutions?<br />
*How can such attributes best combine to form an objective function that can be used to generate Birds of a Feather puzzles through combinatorial optimization algorithms (e.g. simulated annealing)?<br />
<br />
Given this fresh ground for exploration, we would invite educators and students to explore these and other questions concerning Birds of a Feather, and we can summarize our results in a future column.<br />
<br />
The best learning is through experience, and we hope that this grit results in some pearls of work in the months to come. To share your results, please email Todd Neller (tneller@gettysburg.edu) and we invite you to register with and add to our wiki on the subject [[Birds of a Feather]].</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Birds_of_a_Feather&diff=11Birds of a Feather2016-09-27T20:38:30Z<p>ToddNeller: ToddNeller moved page StacksSquared to Birds of a Feather: Better name</p>
<hr />
<div>=StacksSquared Rules=<br />
<br />
FreeCell stands out among solitaire card games because it is essentially a random self-generating puzzle that has perfect information and can be solved with high probability. Players over the years have, as a community, researched many aspects of the game.[http://solitairelaboratory.com/fcfaq.html]<br />
<br />
StacksSquared is an original perfect-information solitaire game played with a standard 52-card deck. After shuffling, the player deals the cards face-up left-to-right in c columns, and top-to-bottom in r rows to create an r-by-c grid of cards.<br />
An example 4-by-4 game's initial layout:<br />
<br />
<nowiki>5S JC QH 8H<br />
KC 6H 3H 9H<br />
3S JS TH TS<br />
KS 7D AH 5C</nowiki><br />
<br />
Think of each grid cell as initially containing a 1-card stack. A stack may be moved on top of another stack in the same row, or in the same column if at least one of two conditions is met: (1) The top card of each stack has the same suit. (2) The top card of each stack has the same rank or an adjacent rank (with Aces low and Kings high and Ace and King non-adjacent). Thus the 9H (9 of Hearts) stack can move onto the TS (Ten of Spades) being adjacent/same in rank:<br />
<br />
<nowiki>5S JC QH 8H <br />
KC 6H 3H <br />
3S JS TH 9H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the 8H stack can move onto the 9H stack being both of (1) same suit and (2) same/adjacent rank:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS TH 8H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the TH stack can move onto the AH stack being of the same suit:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS 8H <br />
KS 7D TH 5C</nowiki><br />
<br />
If we notate each move as the top cards of the moving and destination stacks separated by a hyphen, then this entire tableau can be formed into a single stack from this sequence of moves: <br />
<br />
<nowiki>9H-TS 8H-9H TH-AH 3H-TH QH-3H 6H-7D JC-JS 3S-KS 5S-3S 5C-5S KC-5C QH-KC QH-6H QH-JC QH-8H</nowiki><br />
<br />
Let us call this simple solution concept a "single-stack solution". However, we can define a more general solution concept of forming largest stacks by defining the score of a grid to be the sum of the squares of the stack sizes, hence the name "StacksSquared". The general solution of any grid is a sequence of moves that maximizes this grid score.<br />
<br />
=StacksSquared Questions=<br />
<br />
Having defined the puzzle, we can now ask many interesting questions about the game. For r rows and c columns, <br />
*What is the probability that a deal will have a single-stack solution?<br />
*What is the maximal score distribution of deals?<br />
*What are heuristics that can be used to guide search more efficiently to solutions?<br />
*What are characteristics of grids without single-stack solutions?<br />
<br />
There are also many questions one can ask with regard to the automated design of StacksSquared puzzles:<br />
*What are the most important attributes of challenging deals with single-stack solutions?<br />
*How can such attributes best combine to form an objective function that can be used to generate StacksSquared puzzles through combinatorial optimization algorithms (e.g. simulated annealing)?<br />
<br />
Given this fresh ground for exploration, we would invite educators and students to explore these and other questions concerning StacksSquared, and we can summarize our results in a future column.<br />
<br />
The best learning is through experience, and we hope that this grit results in some pearls of work in the months to come. To share your results, please email Todd Neller (tneller@gettysburg.edu) and we invite you to register with and add to our wiki on the subject [[StacksSquared]].</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=StacksSquared&diff=12StacksSquared2016-09-27T20:38:30Z<p>ToddNeller: ToddNeller moved page StacksSquared to Birds of a Feather: Better name</p>
<hr />
<div>#REDIRECT [[Birds of a Feather]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Birds_of_a_Feather&diff=10Birds of a Feather2016-08-22T21:55:15Z<p>ToddNeller: minor edits</p>
<hr />
<div>=StacksSquared Rules=<br />
<br />
FreeCell stands out among solitaire card games because it is essentially a random self-generating puzzle that has perfect information and can be solved with high probability. Players over the years have, as a community, researched many aspects of the game.[http://solitairelaboratory.com/fcfaq.html]<br />
<br />
StacksSquared is an original perfect-information solitaire game played with a standard 52-card deck. After shuffling, the player deals the cards face-up left-to-right in c columns, and top-to-bottom in r rows to create an r-by-c grid of cards.<br />
An example 4-by-4 game's initial layout:<br />
<br />
<nowiki>5S JC QH 8H<br />
KC 6H 3H 9H<br />
3S JS TH TS<br />
KS 7D AH 5C</nowiki><br />
<br />
Think of each grid cell as initially containing a 1-card stack. A stack may be moved on top of another stack in the same row, or in the same column if at least one of two conditions is met: (1) The top card of each stack has the same suit. (2) The top card of each stack has the same rank or an adjacent rank (with Aces low and Kings high and Ace and King non-adjacent). Thus the 9H (9 of Hearts) stack can move onto the TS (Ten of Spades) being adjacent/same in rank:<br />
<br />
<nowiki>5S JC QH 8H <br />
KC 6H 3H <br />
3S JS TH 9H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the 8H stack can move onto the 9H stack being both of (1) same suit and (2) same/adjacent rank:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS TH 8H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the TH stack can move onto the AH stack being of the same suit:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS 8H <br />
KS 7D TH 5C</nowiki><br />
<br />
If we notate each move as the top cards of the moving and destination stacks separated by a hyphen, then this entire tableau can be formed into a single stack from this sequence of moves: <br />
<br />
<nowiki>9H-TS 8H-9H TH-AH 3H-TH QH-3H 6H-7D JC-JS 3S-KS 5S-3S 5C-5S KC-5C QH-KC QH-6H QH-JC QH-8H</nowiki><br />
<br />
Let us call this simple solution concept a "single-stack solution". However, we can define a more general solution concept of forming largest stacks by defining the score of a grid to be the sum of the squares of the stack sizes, hence the name "StacksSquared". The general solution of any grid is a sequence of moves that maximizes this grid score.<br />
<br />
=StacksSquared Questions=<br />
<br />
Having defined the puzzle, we can now ask many interesting questions about the game. For r rows and c columns, <br />
*What is the probability that a deal will have a single-stack solution?<br />
*What is the maximal score distribution of deals?<br />
*What are heuristics that can be used to guide search more efficiently to solutions?<br />
*What are characteristics of grids without single-stack solutions?<br />
<br />
There are also many questions one can ask with regard to the automated design of StacksSquared puzzles:<br />
*What are the most important attributes of challenging deals with single-stack solutions?<br />
*How can such attributes best combine to form an objective function that can be used to generate StacksSquared puzzles through combinatorial optimization algorithms (e.g. simulated annealing)?<br />
<br />
Given this fresh ground for exploration, we would invite educators and students to explore these and other questions concerning StacksSquared, and we can summarize our results in a future column.<br />
<br />
The best learning is through experience, and we hope that this grit results in some pearls of work in the months to come. To share your results, please email Todd Neller (tneller@gettysburg.edu) and we invite you to register with and add to our wiki on the subject [[StacksSquared]].</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Ed_Column_Ideas&diff=9AI Ed Column Ideas2016-08-22T21:54:00Z<p>ToddNeller: /* StacksSquared */</p>
<hr />
<div>=Challenge Problems=<br />
<br />
The creation and sharing of challenge problems aid the AI educator in that (1) the best education is through experience, and (2) novel challenge problems provide unique experiences, questions, and answers that cannot simply be searched online. <br />
<br />
==StacksSquared==<br />
<br />
FreeCell stands out among solitaire card games because it is essentially a random self-generating puzzle that has perfect information and can be solved with high probability. Players over the years have, as a community, researched many aspects of the game.[http://solitairelaboratory.com/fcfaq.html]<br />
<br />
StacksSquared is an original perfect-information solitaire game played with a standard 52-card deck. After shuffling, the player deals the cards face-up left-to-right in c columns, and top-to-bottom in r rows to create an r-by-c grid of cards.<br />
An example 4-by-4 game's initial layout:<br />
<br />
<nowiki>5S JC QH 8H<br />
KC 6H 3H 9H<br />
3S JS TH TS<br />
KS 7D AH 5C</nowiki><br />
<br />
Think of each grid cell as initially containing a 1-card stack. A stack may be moved on top of another stack in the same row, or in the same column if at least one of two conditions is met: (1) The top card of each stack has the same suit. (2) The top card of each stack has the same rank or an adjacent rank (with Aces low and Kings high and Ace and King non-adjacent). Thus the 9H (9 of Hearts) stack can move onto the TS (Ten of Spades) being adjacent/same in rank:<br />
<br />
<nowiki>5S JC QH 8H <br />
KC 6H 3H <br />
3S JS TH 9H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the 8H stack can move onto the 9H stack being both of (1) same suit and (2) same/adjacent rank:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS TH 8H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the TH stack can move onto the AH stack being of the same suit:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS 8H <br />
KS 7D TH 5C</nowiki><br />
<br />
If we notate each move as the top cards of the moving and destination stacks separated by a hyphen, then this entire tableau can be formed into a single stack from this sequence of moves: <br />
<br />
<nowiki>9H-TS 8H-9H TH-AH 3H-TH QH-3H 6H-7D JC-JS 3S-KS 5S-3S 5C-5S KC-5C QH-KC QH-6H QH-JC QH-8H</nowiki><br />
<br />
Let us call this simple solution concept a "single-stack solution". However, we can define a more general solution concept of forming largest stacks by defining the score of a grid to be the sum of the squares of the stack sizes, hence the name "StacksSquared". The general solution of any grid is a sequence of moves that maximizes this grid score.<br />
<br />
Having defined the puzzle, we can now ask many interesting questions about the game. For r rows and c columns, <br />
*What is the probability that a deal will have a single-stack solution?<br />
*What is the maximal score distribution of deals?<br />
*What are heuristics that can be used to guide search more efficiently to solutions?<br />
*What are characteristics of grids without single-stack solutions?<br />
<br />
There are also many questions one can ask with regard to the automated design of StacksSquared puzzles:<br />
*What are the most important attributes of challenging deals with single-stack solutions?<br />
*How can such attributes best combine to form an objective function that can be used to generate StacksSquared puzzles through combinatorial optimization algorithms (e.g. simulated annealing)?<br />
<br />
Given this fresh ground for exploration, we would invite educators and students to explore these and other questions concerning StacksSquared, and we can summarize our results in a future column.<br />
<br />
The best learning is through experience, and we hope that this grit results in some pearls of work in the months to come. To share your results, please email Todd Neller (tneller@gettysburg.edu) and we invite you to register with and add to our wiki on the subject [[StacksSquared]].<br />
<br />
=Model AI Assignment Highlights=<br />
<br />
We would also invite past publishers of Model AI Assignments to highlight their work and encourage instructors to take advantage of the resources found on the [http://modelai.gettysburg.edu Model AI Assignments website].</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Ed_Column_Ideas&diff=8AI Ed Column Ideas2016-08-22T21:51:35Z<p>ToddNeller: /* StacksSquared */ correction</p>
<hr />
<div>=Challenge Problems=<br />
<br />
The creation and sharing of challenge problems aid the AI educator in that (1) the best education is through experience, and (2) novel challenge problems provide unique experiences, questions, and answers that cannot simply be searched online. <br />
<br />
==StacksSquared==<br />
<br />
FreeCell stands out among solitaire card games because it is essentially a random self-generating puzzle that has perfect information and can be solved with high probability. Players over the years have, as a community, researched many aspects of the game.[http://solitairelaboratory.com/fcfaq.html]<br />
<br />
StacksSquared is an original perfect-information solitaire game played with a standard 52-card deck. After shuffling, the player deals the cards face-up left-to-right in c columns, and top-to-bottom in r rows to create an r-by-c tableau of cards.<br />
An example 4-by-4 game's initial layout:<br />
<br />
<nowiki>5S JC QH 8H<br />
KC 6H 3H 9H<br />
3S JS TH TS<br />
KS 7D AH 5C</nowiki><br />
<br />
Think of each grid cell as initial containing a 1-card stack. A stack may be moved on top of another stack in the same row, or in the same column if at least one of two conditions is met: (1) The top card of each stack has the same suit. (2) The top card of each stack has the same rank or an adjacent rank (with Aces low and Kings high and Ace and King non-adjacent). Thus the 9H (9 of Hearts) stack can move onto the TS (Ten of Spades) being adjacent/same in rank:<br />
<br />
<nowiki>5S JC QH 8H <br />
KC 6H 3H <br />
3S JS TH 9H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the 8H stack can move onto the 9H stack being both of (1) same suit and (2) same/adjacent rank:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS TH 8H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the TH stack can move onto the AH stack being of the same suit:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS 8H <br />
KS 7D TH 5C</nowiki><br />
<br />
If we notate each move as a the top cards of the moving and destination stacks separated by a hyphen, then this entire tableau can be formed into a single stack from this sequence of moves: <br />
<br />
<nowiki>9H-TS 8H-9H TH-AH 3H-TH QH-3H 6H-7D JC-JS 3S-KS 5S-3S 5C-5S KC-5C QH-KC QH-6H QH-JC QH-8H</nowiki><br />
<br />
Let us call this simple solution concept a "single-stack solution". However, we can form a more general solution concept of forming largest stacks by defining the score of a grid to be the sum of the squares of the stack sizes, hence the name "StacksSquared". The general solution of any grid is a sequence of moves that maximizes this grid score.<br />
<br />
Having defined the puzzle, we can now ask many interesting questions about the game. For r rows and c columns, <br />
*What is the probability that a deal will have a single-stack solution?<br />
*What is the maximal score distribution of deals?<br />
*What are heuristics that can be used to guide search more efficiently to solutions?<br />
*What are characteristics of grids without single-stack solutions?<br />
<br />
There are also many questions one can ask with regard to the automated design of StacksSquared puzzles:<br />
*What are the most important attributes of challenging deals with single-stack solutions?<br />
*How can such attributes best combine to form an objective function that can be used to generate StacksSquared puzzles through combinatorial optimization algorithms (e.g. simulated annealing)?<br />
<br />
Given this fresh ground for exploration, we would invite educators and students to explore these and other questions concerning StacksSquared, and we can summarize our results in a future column.<br />
<br />
The best learning is through experience, and we hope that this grit results in some pearls of work in the months to come. To share your results, please email Todd Neller (tneller@gettysburg.edu) and we invite you to register with and add to our wiki on the subject [[StacksSquared]].<br />
<br />
=Model AI Assignment Highlights=<br />
<br />
We would also invite past publishers of Model AI Assignments to highlight their work and encourage instructors to take advantage of the resources found on the [http://modelai.gettysburg.edu Model AI Assignments website].</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Ed_Column_Ideas&diff=7AI Ed Column Ideas2016-08-22T21:47:02Z<p>ToddNeller: Intro StacksSquared edit</p>
<hr />
<div>=Challenge Problems=<br />
<br />
The creation and sharing of challenge problems aid the AI educator in that (1) the best education is through experience, and (2) novel challenge problems provide unique experiences, questions, and answers that cannot simply be searched online. <br />
<br />
==StacksSquared==<br />
<br />
FFreeCell stands out among solitaire card games because it is essentially a random self-generating puzzle that has perfect information and can be solved with high probability. Players over the years have, as a community, researched many aspects of the game.[http://solitairelaboratory.com/fcfaq.html]<br />
<br />
StacksSquared is an original perfect-information solitaire game played with a standard 52-card deck. After shuffling, the player deals the cards face-up left-to-right in c columns, and top-to-bottom in r rows to create an r-by-c tableau of cards.<br />
An example 4-by-4 game's initial layout:<br />
<br />
<nowiki>5S JC QH 8H<br />
KC 6H 3H 9H<br />
3S JS TH TS<br />
KS 7D AH 5C</nowiki><br />
<br />
Think of each grid cell as initial containing a 1-card stack. A stack may be moved on top of another stack in the same row, or in the same column if at least one of two conditions is met: (1) The top card of each stack has the same suit. (2) The top card of each stack has the same rank or an adjacent rank (with Aces low and Kings high and Ace and King non-adjacent). Thus the 9H (9 of Hearts) stack can move onto the TS (Ten of Spades) being adjacent/same in rank:<br />
<br />
<nowiki>5S JC QH 8H <br />
KC 6H 3H <br />
3S JS TH 9H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the 8H stack can move onto the 9H stack being both of (1) same suit and (2) same/adjacent rank:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS TH 8H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the TH stack can move onto the AH stack being of the same suit:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS 8H <br />
KS 7D TH 5C</nowiki><br />
<br />
If we notate each move as a the top cards of the moving and destination stacks separated by a hyphen, then this entire tableau can be formed into a single stack from this sequence of moves: <br />
<br />
<nowiki>9H-TS 8H-9H TH-AH 3H-TH QH-3H 6H-7D JC-JS 3S-KS 5S-3S 5C-5S KC-5C QH-KC QH-6H QH-JC QH-8H</nowiki><br />
<br />
Let us call this simple solution concept a "single-stack solution". However, we can form a more general solution concept of forming largest stacks by defining the score of a grid to be the sum of the squares of the stack sizes, hence the name "StacksSquared". The general solution of any grid is a sequence of moves that maximizes this grid score.<br />
<br />
Having defined the puzzle, we can now ask many interesting questions about the game. For r rows and c columns, <br />
*What is the probability that a deal will have a single-stack solution?<br />
*What is the maximal score distribution of deals?<br />
*What are heuristics that can be used to guide search more efficiently to solutions?<br />
*What are characteristics of grids without single-stack solutions?<br />
<br />
There are also many questions one can ask with regard to the automated design of StacksSquared puzzles:<br />
*What are the most important attributes of challenging deals with single-stack solutions?<br />
*How can such attributes best combine to form an objective function that can be used to generate StacksSquared puzzles through combinatorial optimization algorithms (e.g. simulated annealing)?<br />
<br />
Given this fresh ground for exploration, we would invite educators and students to explore these and other questions concerning StacksSquared, and we can summarize our results in a future column.<br />
<br />
The best learning is through experience, and we hope that this grit results in some pearls of work in the months to come. To share your results, please email Todd Neller (tneller@gettysburg.edu) and we invite you to register with and add to our wiki on the subject [[StacksSquared]].<br />
<br />
<br />
=Model AI Assignment Highlights=<br />
<br />
We would also invite past publishers of Model AI Assignments to highlight their work and encourage instructors to take advantage of the resources found on the [http://modelai.gettysburg.edu Model AI Assignments website].</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Birds_of_a_Feather&diff=6Birds of a Feather2016-08-22T21:46:12Z<p>ToddNeller: Create StacksSquared page</p>
<hr />
<div>=StacksSquared Rules=<br />
<br />
FreeCell stands out among solitaire card games because it is essentially a random self-generating puzzle that has perfect information and can be solved with high probability. Players over the years have, as a community, researched many aspects of the game.[http://solitairelaboratory.com/fcfaq.html]<br />
<br />
StacksSquared is an original perfect-information solitaire game played with a standard 52-card deck. After shuffling, the player deals the cards face-up left-to-right in c columns, and top-to-bottom in r rows to create an r-by-c tableau of cards.<br />
<br />
An example 4-by-4 game's initial layout:<br />
<br />
<nowiki>5S JC QH 8H<br />
KC 6H 3H 9H<br />
3S JS TH TS<br />
KS 7D AH 5C</nowiki><br />
<br />
Think of each grid cell as initial containing a 1-card stack. A stack may be moved on top of another stack in the same row, or in the same column if at least one of two conditions is met: (1) The top card of each stack has the same suit. (2) The top card of each stack has the same rank or an adjacent rank (with Aces low and Kings high and Ace and King non-adjacent). Thus the 9H (9 of Hearts) stack can move onto the TS (Ten of Spades) being adjacent/same in rank:<br />
<br />
<nowiki>5S JC QH 8H <br />
KC 6H 3H <br />
3S JS TH 9H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the 8H stack can move onto the 9H stack being both of (1) same suit and (2) same/adjacent rank:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS TH 8H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the TH stack can move onto the AH stack being of the same suit:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS 8H <br />
KS 7D TH 5C</nowiki><br />
<br />
If we notate each move as a the top cards of the moving and destination stacks separated by a hyphen, then this entire tableau can be formed into a single stack from this sequence of moves: <br />
<br />
<nowiki>9H-TS 8H-9H TH-AH 3H-TH QH-3H 6H-7D JC-JS 3S-KS 5S-3S 5C-5S KC-5C QH-KC QH-6H QH-JC QH-8H</nowiki><br />
<br />
Let us call this simple solution concept a "single-stack solution". However, we can form a more general solution concept of forming largest stacks by defining the score of a grid to be the sum of the squares of the stack sizes, hence the name "StacksSquared". The general solution of any grid is a sequence of moves that maximizes this grid score.<br />
<br />
=StacksSquared Questions=<br />
<br />
Having defined the puzzle, we can now ask many interesting questions about the game. For r rows and c columns, <br />
*What is the probability that a deal will have a single-stack solution?<br />
*What is the maximal score distribution of deals?<br />
*What are heuristics that can be used to guide search more efficiently to solutions?<br />
*What are characteristics of grids without single-stack solutions?<br />
<br />
There are also many questions one can ask with regard to the automated design of StacksSquared puzzles:<br />
*What are the most important attributes of challenging deals with single-stack solutions?<br />
*How can such attributes best combine to form an objective function that can be used to generate StacksSquared puzzles through combinatorial optimization algorithms (e.g. simulated annealing)?<br />
<br />
Given this fresh ground for exploration, we would invite educators and students to explore these and other questions concerning StacksSquared, and we can summarize our results in a future column.<br />
<br />
The best learning is through experience, and we hope that this grit results in some pearls of work in the months to come. To share your results, please email Todd Neller (tneller@gettysburg.edu) and we invite you to register with and add to our wiki on the subject [[StacksSquared]].</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Ed_Column_Ideas&diff=5AI Ed Column Ideas2016-08-22T21:44:18Z<p>ToddNeller: Creation of column idea page</p>
<hr />
<div>=Challenge Problems=<br />
<br />
The creation and sharing of challenge problems aid the AI educator in that (1) the best education is through experience, and (2) novel challenge problems provide unique experiences, questions, and answers that cannot simply be searched online. <br />
<br />
==StacksSquared==<br />
<br />
FreeCell stands out among solitaire card games because it is essentially a random self-generating puzzle that has perfect information and can be solved with high probability. Users[http://solitairelaboratory.com/fcfaq.html]<br />
<br />
StacksSquared is an original solitaire game played with a standard 52-card deck. After shuffling, the player deals the cards face-up left-to-right in c columns, and top-to-bottom in r rows to create an r-by-c tableau of cards.<br />
<br />
An example 4-by-4 game's initial layout:<br />
<br />
<nowiki>5S JC QH 8H<br />
KC 6H 3H 9H<br />
3S JS TH TS<br />
KS 7D AH 5C</nowiki><br />
<br />
Think of each grid cell as initial containing a 1-card stack. A stack may be moved on top of another stack in the same row, or in the same column if at least one of two conditions is met: (1) The top card of each stack has the same suit. (2) The top card of each stack has the same rank or an adjacent rank (with Aces low and Kings high and Ace and King non-adjacent). Thus the 9H (9 of Hearts) stack can move onto the TS (Ten of Spades) being adjacent/same in rank:<br />
<br />
<nowiki>5S JC QH 8H <br />
KC 6H 3H <br />
3S JS TH 9H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the 8H stack can move onto the 9H stack being both of (1) same suit and (2) same/adjacent rank:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS TH 8H <br />
KS 7D AH 5C</nowiki><br />
<br />
And the TH stack can move onto the AH stack being of the same suit:<br />
<br />
<nowiki>5S JC QH <br />
KC 6H 3H <br />
3S JS 8H <br />
KS 7D TH 5C</nowiki><br />
<br />
If we notate each move as a the top cards of the moving and destination stacks separated by a hyphen, then this entire tableau can be formed into a single stack from this sequence of moves: <br />
<br />
<nowiki>9H-TS 8H-9H TH-AH 3H-TH QH-3H 6H-7D JC-JS 3S-KS 5S-3S 5C-5S KC-5C QH-KC QH-6H QH-JC QH-8H</nowiki><br />
<br />
Let us call this simple solution concept a "single-stack solution". However, we can form a more general solution concept of forming largest stacks by defining the score of a grid to be the sum of the squares of the stack sizes, hence the name "StacksSquared". The general solution of any grid is a sequence of moves that maximizes this grid score.<br />
<br />
Having defined the puzzle, we can now ask many interesting questions about the game. For r rows and c columns, <br />
*What is the probability that a deal will have a single-stack solution?<br />
*What is the maximal score distribution of deals?<br />
*What are heuristics that can be used to guide search more efficiently to solutions?<br />
*What are characteristics of grids without single-stack solutions?<br />
<br />
There are also many questions one can ask with regard to the automated design of StacksSquared puzzles:<br />
*What are the most important attributes of challenging deals with single-stack solutions?<br />
*How can such attributes best combine to form an objective function that can be used to generate StacksSquared puzzles through combinatorial optimization algorithms (e.g. simulated annealing)?<br />
<br />
Given this fresh ground for exploration, we would invite educators and students to explore these and other questions concerning StacksSquared, and we can summarize our results in a future column.<br />
<br />
The best learning is through experience, and we hope that this grit results in some pearls of work in the months to come. To share your results, please email Todd Neller (tneller@gettysburg.edu) and we invite you to register with and add to our wiki on the subject [[StacksSquared]].<br />
<br />
<br />
=Model AI Assignment Highlights=<br />
<br />
We would also invite past publishers of Model AI Assignments to highlight their work and encourage instructors to take advantage of the resources found on the [http://modelai.gettysburg.edu Model AI Assignments website].</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Education&diff=4AI Education2016-08-22T19:44:00Z<p>ToddNeller: </p>
<hr />
<div>[[AI Ed Column Ideas]]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=AI_Education&diff=3AI Education2016-08-22T19:43:35Z<p>ToddNeller: Created page with "[Column Ideas]"</p>
<hr />
<div>[Column Ideas]</div>ToddNellerhttp://cs.gettysburg.edu/ai-matters/index.php?title=Main_Page&diff=2Main Page2016-08-22T19:42:23Z<p>ToddNeller: Create link to AI Matters AI Education page</p>
<hr />
<div>[[AI Education]]</div>ToddNeller