- Computational Intelligence
Homework Assignment
Train a neuron
using the Perceptron Learning Rule, taking:
c = 1
w1 = [0 1 0]t
( x1 = [2 1 -1]t , d1 = -1 )
( x2 = [0 -1 -1]t , d2 = 1 )
Repeat the (x1,
d1), (x2, d2)
sequence until you obtain the correct outputs. Do not use a computer (except
for typing).
Implement a classifier for characters L and I using
the discrete perceptron learning algorithm. You may use any implementation,
including the one in Ch. 2 (textbook).
Specifications:
·
Use a
3 x 3 binary matrix representation.
·
Your
neural network should have one neuron.
What happens when the letters are “noisy”?
Turn in the hard copy of the code and the
numerical results.
You may use any implementation, including the ones in
Ch. 3 (textbook) and Weka.
Turn in the numerical results, function plots, and
your conclusions. Describe which implementation you have used and, if it is
your code, attach it.
No comments:
Post a Comment