leakyReluLayer

Leaky Rectified Linear Unit (ReLU) layer

Description

A leaky ReLU layer performs a threshold operation, where any input value less than zero is multiplied by a fixed scalar.

This operation is equivalent to:

$$f(x)=\{\begin{array}{ll}x,\hfill & x\ge 0\hfill \\ scale*x,\hfill & x<0\hfill \end{array}.$$

Creation

Syntax

layer = leakyReluLayer

layer = leakyReluLayer(scale)

layer = leakyReluLayer(___,'Name',Name)

Description

layer = leakyReluLayer returns a leaky ReLU layer.

layer = leakyReluLayer(scale) returns a leaky ReLU layer with a scalar multiplier for negative inputs equal to scale.

layer = leakyReluLayer(___,'Name',Name) returns a leaky ReLU layer and sets the optional Name property.

Properties

Leaky ReLU

Scale — Scalar multiplier for negative input values

0.01 (default) | finite real scalar

Scalar multiplier for negative input values, specified as a finite real scalar.

Example: 0.4

Layer

Name — Layer name

"" (default) | character vector | string scalar

Layer name, specified as a character vector or string scalar. For Layer array input, the trainnet and dlnetwork functions automatically assign names to layers with the name "".

The LeakyReLULayer object stores this property as a character vector.

Data Types: char | string

NumInputs — Number of inputs

1 (default)

This property is read-only.

Number of inputs to the layer, returned as 1. This layer accepts a single input only.

Data Types: double

InputNames — Input names

{'in'} (default)

This property is read-only.

Input names, returned as {'in'}. This layer accepts a single input only.

Data Types: cell

NumOutputs — Number of outputs

1 (default)

This property is read-only.

Number of outputs from the layer, returned as 1. This layer has a single output only.

Data Types: double

OutputNames — Output names

{'out'} (default)

This property is read-only.

Output names, returned as {'out'}. This layer has a single output only.

Data Types: cell

Examples

Create Leaky ReLU Layer

Create a leaky ReLU layer with the name 'leaky1' and a scalar multiplier for negative inputs equal to 0.1.

layer = leakyReluLayer(0.1,'Name','leaky1')

layer = 
  LeakyReLULayer with properties:

     Name: 'leaky1'

   Hyperparameters
    Scale: 0.1000

Include a leaky ReLU layer in a Layer array.

layers = [
    imageInputLayer([28 28 1])
    convolution2dLayer(3,16)
    batchNormalizationLayer
    leakyReluLayer
    
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(3,32)
    batchNormalizationLayer
    leakyReluLayer
    
    fullyConnectedLayer(10)
    softmaxLayer]

layers = 
  10x1 Layer array with layers:

     1   ''   Image Input           28x28x1 images with 'zerocenter' normalization
     2   ''   2-D Convolution       16 3x3 convolutions with stride [1  1] and padding [0  0  0  0]
     3   ''   Batch Normalization   Batch normalization
     4   ''   Leaky ReLU            Leaky ReLU with scale 0.01
     5   ''   2-D Max Pooling       2x2 max pooling with stride [2  2] and padding [0  0  0  0]
     6   ''   2-D Convolution       32 3x3 convolutions with stride [1  1] and padding [0  0  0  0]
     7   ''   Batch Normalization   Batch normalization
     8   ''   Leaky ReLU            Leaky ReLU with scale 0.01
     9   ''   Fully Connected       10 fully connected layer
    10   ''   Softmax               softmax

Algorithms

Layer Input and Output Formats

Layers in a layer array or layer graph pass data to subsequent layers as formatted dlarray objects. The format of a dlarray object is a string of characters in which each character describes the corresponding dimension of the data. The formats consist of one or more of these characters:

• "S" — Spatial

• "C" — Channel

• "B" — Batch

• "T" — Time

• "U" — Unspecified

For example, you can describe 2-D image data that is represented as a 4-D array, where the first two dimensions correspond to the spatial dimensions of the images, the third dimension corresponds to the channels of the images, and the fourth dimension corresponds to the batch dimension, as having the format "SSCB" (spatial, spatial, channel, batch).

LeakyReLULayer objects apply an element-wise operation and supports input data of any format. The layer and does not add or remove any dimensions, so it outputs data with the same format as its inputs.

References

[1] Maas, Andrew L., Awni Y. Hannun, and Andrew Y. Ng. "Rectifier nonlinearities improve neural network acoustic models." In Proc. ICML, vol. 30, no. 1. 2013.

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using MATLAB® Coder™.

GPU Code Generation
Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.

Version History

Introduced in R2017b