Developer Guide for Intel® Data Analytics Acceleration Library 2019 Update 1

Local Contrast Normalization Backward Layer

For given dimensions k 1 of size n k 1 , k 2 of size n k 2 , and f different from k 1 and k 2, the forward local contrast normalization layer normalizes the input p-dimensional tensor X R n 1 x n 2 x ... x n p . For more details, see Forward Local Contrast Normalization Layer.

The library supports four-dimensional input tensors XR n 1 x n 2 x n 3 x n 4 .

Without loss of generality let's assume that backward local contrast normalization is applied to the last two dimensions. The backward local contrast normalization layer takes:

The layer computes the four-dimensional value tensor ZR n 1 x n 2 x n 3 x n 4 :



Problem Statement

The computation depends on whether the dimension f is set:

Consequently: