SoftMaxLayer

Full name Microsoft.VisualBasic.MachineLearning.CNN.losslayers.SoftMaxLayer Assembly Microsoft.VisualBasic.DeepLearning Members 4

This layer will squash the result of the activations in the fully connected layer and give you a value of 0 to 1 for all output activations.

@author Daniel Persson (mailto.woden@gmail.com)

01 Syntax

Microsoft.VisualBasic.MachineLearning.CNN.losslayers.SoftMaxLayer

02 Methods

Name	Overloads	Summary
backward	1	compute and accumulate gradient wrt weights and bias of this layer
forward	1
ToString	1

03 Properties

Name	Overloads	Summary
Type	1

04 Members

method backward #

backward(Int32)

compute and accumulate gradient wrt weights and bias of this layer

Parameters

Name	Type	Description
`y`	`Int32`	-

property Type #

Type

method forward #

forward(DataBlock, Boolean)

method ToString #

ToString()