Loss Logistic Cross-entropy Backward Layer

For a two-dimensional input tensor XR n 1 x 1 with batch dimension of size n 1 and two-dimensional TR n 1 x 1, the layer computes a one-dimensional tensor with the logistic cross-entropy value. For more details, see Forward Loss Logistic Cross-entropy Layer.

The backward loss logistic cross-entropy layer for a given two-dimensional tensor XR n 1 x 1 and two-dimensional TR n 1 x 1 computes the two-dimensional tensor ZR n 1 x 1 such that



where

  • pr i [0,1] is the probability that a sample belongs to the first of two classes

For more complete information about compiler optimizations, see our Optimization Notice.
Select sticky button color: 
Orange (only for download buttons)