Notes

Outline

CS 371: Introduction to Artificial Intelligence Neural Networks

Machine Learning Learning is such an important part of what we consider "intelligence" that it appears in one common definition: intelligence: the ability to learn or understand or to deal with new or trying situations. (Webster's) Intelligent agents make mistakes, but one might argue that they don't make the same mistakes perpetually.

What do agents learn? If-then decision structures (decision trees) Function approximation (neural networks) Action (control) policy (reinforcement learning) etc. à lots of things! Learning agents have at least one adaptive component of their architecture.

Connectionism Connectionism – intelligence bottom up Small, simple components Connected together in a large network Give rise to complex (intelligent) behaviors. Can complex behavior be learned from a simple process? Our brief foray into artificial neural networks (ANNs) will limit itself to a few simple goals:

Goals Understand the perceptron, the basic unit of ANN computation (like transistor is to circuits), the perceptron learning rule, the class of functions a perceptron can represent, multilayer feed-forward networks, the back-propogation learning algorithm, and the momentum variant of back-propogation. Experience the strengths/weaknesses of multilayer feed-forward methods through experimentation.

The Neuron

The Neuron (cont.) Basic unit of brain computation Dendrites many local to cell body senses input Axon one reaching ~1cm from cell body transmits output Axons connect to dendrites through synapses

The Neuron (cont.) Complex electrochemical process: Synapses release chemicals… Chemicals increase dendrite electrical potential… When potential reaches a threshold, … An electrical pulse (action potential) goes down axon to synapses, so … Synapses release chemicals…

Computer & Brain – a comparison Computers have a much faster clock speed. Brains are much, much more parallel. à more unit updates per sec than computer Brains are more adaptive à grow into tasks Brains exhibit graceful degradation: gradual rather than sharp drop off in performance and conditions worsen

Motivation for Neural Network Brain has many desirable characteristics that most computers lack plasticity, self-adaptivity massive parallelism graceful degradation What would be a simple computation unit from which to build a "computer brain"?

The Neural Network Unit weighted sum of inputs: ini = sumj(Wj,i´aj) output from activation function: aj = g(ini)

Activation Functions (a) t = step threshold (can replace with extra input weight W0,i = t & fixed a0 = -1) (c) sigmoid(x) = 1/(1 + e-x)

Understanding What Units Compute Suppose you have a 2-input unit with a step function and a fixed threshold t. Let x, y be inputs. What set of points on the x-y plane are at the unit's threshold? (Simplify equations.) Answer: The line Wx,i´x + Wy,i´y = t rewritten: y = (-Wx,i/Wy,i)x + (t/Wy,i)

In-Class Exercise: Units as Logic Gates For values 0,1 corresponding to true, false, and a unit with a 0/1-step function, can you choose W1,i, W2,i, and t so as to compute: AND? OR? IMPLIES? EQUIVALENT?

In-Class Exercise: Units as Logic Gates For values 0,1 corresponding to true, false, and a unit with a 0/1-step function, can you choose W1,i, W2,i, and t so as to compute: AND? (1, 1, 1.5) OR? (1, 1, .5) IMPLIES? (1, -1, .5) EQUIVALENT? (NOT POSSIBLE – Why?)

Linear Separability One 2-input unit activates for all inputs on one side of a line 3-inputs à plane,  n-inputs à hyperplane

3-Input Unit and Plane of Separation

Perceptrons A perceptron has input units Ij input weights Wj step activation function step0 output O O = step0(sumj(Wj´Ij))

Perceptron Learning Rule Suppose one randomizes initial weights and has a set of desired input, output pairs. Iterate: Compute O from inputs Compute error Err = T – O from correct output T Adjust weights: Wj ß Wj + a´Ij´Err where a is the learning rate.

Perceptron Learning Perceptron learning is a gradient descent search through the space of possible weights. Each training example provides an "error surface" for weights.  Learning rule runs weights downhill with learning rate a as step size. For linearly separable functions, there are no local minima, and guaranteed to converge if learning rate a not too high (overshoot) Summary: Very effective for very simple representable functions.

Network Learning Algorithm

Is There Hope? Is there any hope for learning functions that are not linearly separable? Yes, but a perceptron network isn't enough. One needs more than one layer of units between inputs and outputs to compute other functions. With enough "hidden" units (units within), any boolean function is computable, and any continuous function is approximable.

Simple Multilayer Feed-Forward Network

Multilayer Feed-Forward Network with 1 Hidden Layer

Back-Propagation Basic idea: Supply training inputs, computation feeds forward, error computed with training output, error propagates backward for weight updates. Start with final layer Update output weights of layer according to layer output error as with perceptron learning rule Assign error to units of previous layer according to weights Repeat this process backwards through layers

Back-Propagation (cont.) Error computation makes use of the slope of the activation function, so we need to use continuous activation functions. The sigmoid function is typical. sigmoid(x) = 1/(1 + e-x) sigmoid'(x) = sigmoid(x)(1 – sigmoid(x))  Error term Di = Erri*g'(ini)

Back-Propagation (cont.) Updates to output units: W'j,i ß Wj,i + a´aj´Di Computation of error for previous layer units: Dj ß g'(inj) ´ sumi(Wj,i´Di) Process continues with previous layer: W'k,j ß Wk,j + a´ak´Dj Dk ß g'(ink) ´ sumj(Wk,j´Dj) Repeat until input layer is reached (e.g. ak = Ik)

Slide 28

Momentum When updating a weight, also add the previous update to that weight times a momentum constant m (0.0 <= m < 1.0). Possible to carry weights across plateaux in error surface through local minima to global minima through global minima to local minima (i.e. can have undesirable effects as well).

Error Surface

Text Notation