RectifiedLinearUnitsLayer

Full name Microsoft.VisualBasic.MachineLearning.CNN.layers.RectifiedLinearUnitsLayer Assembly Microsoft.VisualBasic.DeepLearning Members 5

This is a layer of neurons that applies the non-saturating activation function f(x)=max(0,x). It increases the nonlinear properties of the decision function and of the overall network without affecting the receptive fields of the convolution layer.

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

00 Remarks

ReLU

01 Syntax

Microsoft.VisualBasic.MachineLearning.CNN.layers.RectifiedLinearUnitsLayer

02 Methods

Name	Overloads	Summary
forward	1
backward	1
ToString	1

03 Properties

Name	Overloads	Summary
BackPropagationResult	1
Type	1

04 Members

property BackPropagationResult #

BackPropagationResult

property Type #

Type

method forward #

forward(DataBlock, Boolean)

method backward #

backward()

method ToString #

ToString()