Documentation

reluLayer

Create a Rectified Linear Unit (ReLU) layer

collapse all in page

Syntax

layer = reluLayer()
layer = reluLayer(Name,Value)

Description

layer= reluLayer()返回一个修正线性单元(ReLU)层。这页erforms a threshold operation to each element, where any input value less than zero is set to zero, i.e.,

f ( x ) = { x , x ≥ 0 0 , x < 0 .

The ReLU layer does not change the size of its input.

example

layer= reluLayer(Name,Value)returns a ReLU layer, with the additional option specified by theName,Valuepair argument.

Examples

collapse all

Create a rectified linear unit layer with the namerelu1.

layer = reluLayer('Name','relu1');

Input Arguments

collapse all

Name-Value Pair Arguments

Example:'Name','relu1'specifies the name of the layer asrelu1.

Specify optional comma-separated pair ofName,Valueargument.Nameis the argument name andValueis the corresponding value.Namemust appear inside single quotes (' ').

collapse all

Name for the layer, specified as the comma-separated pair consisting ofNameand a character vector.

Data Types:char

Output Arguments

collapse all

Rectified linear unit layer, returned as aReLULayerobject.

For information on concatenating layers to construct convolutional neural network architecture, seeLayer.

References

[1] Nair, V. and G. E. Hinton. Rectified linear units improve restricted boltzmann machines. In Proc. 27th International Conference on Machine Learning, 2010.

See Also

Introduced in R2016a

Was this topic helpful?
Neural Network Toolbox Documentation
Other Documentation
金宝app

MATLAB、Simulink、その他の製品をお試しください

無料評価版のダウンロード