[英]How to reinforce forward propagation signal in deep learning network?
I've asked a question earlier at Matconvnet output of deep network's marix is uniform valued instead of varying values?我之前在Matconvnet 上问过一个问题,深度网络的 marix 输出是统一值而不是变化值? As I debugged the deep network for density estimation, I realized the signal towards the output dies out/fades.
当我调试用于密度估计的深度网络时,我意识到输出的信号消失/衰减。 How can I reinforce the signal so that it doesn't become flat- and the peak and base values keep a high amplitude?
我怎样才能加强信号,使其不会变得平坦 - 并且峰值和基值保持高幅度?
在 LRN 归一化中使用较低的 alpha 可以增强输出。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.