__deep of LRN Local response in depth learning technology

LRN (local Response normalization) partial response normalized notes

This Note Records Learning LRN (local Response normalization), if there are errors, please criticize and learn to communicate. 1. Side inhibition (lateral inhibition)

2. Calculation Formula

Hinton in the 2012 Alexnet network, its specific formula is given as follows:

The formula looks more complicated, but it's very simple to understand. I represents the first kernel at position (x,y) using the output of the activation function Relu, n is the number of adjacent kernal maps at the same position, n is the total number of kernal. Parameter K,n,alpha,belta are all super parameters and are generally set to k=2,n=5,aloha=1*e-4,beta=0.75.

3. Late controversy

In 2015 Very Deep convolutional Networks for large-scale Image recognition. It's basically useless to mention LRN.

This concept was first proposed in the Alexnet model.
Reference documents:

[Lrn]:imagenet classification with Deep convolutional neural Networks