Discuss  the neuron network paper by Cheng and Titterington(1994, Statistical Science 1994, page 2-30)

1. The McCulloch-Pitts neuron : binary input  and output, connection weight,bias

2. Training method:  compared with least squares ; steepest decent.
     (note : 1. NN trains sample one at a time. 2. The least squares leads to Fisher's linear discriminant rule)

3. Generalization : 3.1. other activation functions (has to be monotonic)
                             3.2 .  hidden layers.
                                    y= max (x_1, x_2)
                                  (need 4 nodes in the hidden layer)
                                  (Note: it is not uncommon to have more hidden units than input units; anti-dimension reduction?)
                            3.3.  Error backpropagation method.