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


class MPSCNNLogSoftMax : MPSCNNKernel


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:

pixel = pixel(x,y,k)) - ln{sum(exp(pixel(x,y,0)) ... exp(pixel(x,y,N-1))}

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


Inherits From

Conforms To

See Also

Softmax Layers

class MPSCNNSoftMax

A neural transfer function that is useful for classification tasks.

class MPSCNNLogSoftMaxGradient

A gradient logarithmic softmax filter.

class MPSCNNSoftMaxGradient

A gradient softmax filter.