Contents

MPSCNNLogSoftMax

A neural transfer function that is useful for constructing a loss function to be minimized when training neural networks.

Declaration

class MPSCNNLogSoftMax

Overview

The logarithmic softmax filter is calculated by taking the natural logarithm of the result of a softmax filter.

For each feature channel per pixel in an image in a feature map, the logarithmic softmax filter computes the following:

[Image]

Where R is the result channel in the pixel, N is the number of feature channels, and y=ln(x) satisfies e``ʸ``=x.

See Also

Softmax Layers