ECE449, Intelligent Systems Engineering
in the assignment box in the ETLC atrium
Note: Show your work! Marks are allocated
for technique and not just the answer.
1. [4 points] Briefly compare neurons used in a) perceptron-type networks and b) RBF-type networks.
[Hint: concentrate on what they compare, how tot is calculated, and how neuron output is determined]
2. [6 points] Consider the modified Hebbian learning rule
= w (1− α)+hx o
and assume the following values xi = oj = 1, learning rate = 1, forgetting factor = 0.1, and initial
w = 0
a) Compare standard ( = 0) and modified Hebbian learning by plotting weights over 30 subsequent
learning steps (i.e. plot
as a function of time) using the parameters provided.
b) Determine maximum value of weight w that can be obtained by modified Hebbian learning using the
parameters provided [Hint: in the limit case, the values of
would be identical].