How to reinforce forward propagation signal in deep learning network?

Question

I've asked a question earlier at Matconvnet output of deep network's marix is uniform valued instead of varying values? As I debugged the deep network for density estimation, I realized the signal towards the output dies out/fades. How can I reinforce the signal so that it doesn't become flat- and the peak and base values keep a high amplitude?

This does not seem to be a programming problem as the question stands now.. — Dr. Snoopy, Sep 30 '17 at 21:54

score 1 · Answer 1 · answered Oct 04 '17 at 13:45

1

Using lower alpha in LRN normalization can reinforce the output.

answered Oct 04 '17 at 13:45

user8701029

11
2

How to reinforce forward propagation signal in deep learning network?

1 Answers1