Figure - PMC

Skip to main content

View full-text article in PMC

. Author manuscript; available in PMC: 2015 May 1.

Published in final edited form as: Artif Intell. 2014 Feb 24;210:78–122. doi: 10.1016/j.artint.2014.02.004

Figure 9.13 — Comparison of $E (O_{i}^{l} O_{j}^{h})$ to 0 for pairs of non-input neurons that are not directly connected to each other in a MNIST classifier network, before and after training. As shown in the previous figure, $W_{i}^{l} W_{j}^{h}$ provides a better approximation. Histograms are obtained by taking 100,000 pairs of unconnected neurons, uniformly at random, and aggregating the results over 10 random input vectors.