How to reinforce forward propagation signal in deep learning network?

92 Views Asked by At

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?enter image description here

1

There are 1 best solutions below

0
user8701029 On

Using lower alpha in LRN normalization can reinforce the output.