(a) Design a two-layer network of perceptrons that implements the Boolean
function (not A ^ not B) V (A ^ B).

(b) Consider a two-layer feedforward neural network with two inputs a
and b, one hidden unit c, and one output unit d. This network has five
weights (wca, wcb, wc0, wdc, wd0), where wx0 represents the bias
weight for unit x. Initialise these weights to the values (0.1, 0.1,
0.1, 0.1, 0.1), then give their values after two training iterations
of the
Backpropagation algorithm. Assume a learning rate
  a  b d 
-----------
  0  1 0
  1  0 1

---

Clarification of Question by shyamvaran-ga on 18 Sep 2004 11:16 PDT

for (a) you can give the answer in form of letters as symbols and I
can convert it into perceptron model.

for (b) please explain in short the steps as well, if you want to
answer one of the two parts let me know.
Thanks