1. [M31] Let us consider the following loading problem:

L =



((−1, 0)



, 0.1), ((1, 0)



, 0.9), ((0, 1)



, 0.9), ((0,−5)



, 0.9)



.

This is clearly a linearly-separable problem. Suppose we are using an LTU network with a logistic sigmoidal neuron and quadratic error function. In addition, suppose that the decision is based on the following thresholding criterion: Ifx < 0.1 then the class is −, whereas the class is + if x > 0.9, and there is no decision in the remaining range of x. Prove that there exists a stationary point that does not yield a separating solution.36