© 2000 Todd Neller.
A.I.M.A. t
ext
figures
© 1995 Prentice Hall.
Used by
permission.
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:
W
j
ß
W
j
+
a
´
I
j
´
Err
where
a
is the
learning rate.
