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