Simplified Information Maximization for Improving Generalization Performance in Multilayered Neural Networks

Figure 11

Information for eight hidden layers as a function of the parameter for the rebel participation data.

(a) 1st layer

(b) 2nd layer

(c) 3rd layer

(d) 4th layer

(e) 5th layer

(f) 6th layer

(g) 7th layer

(h) 8th layer