clippedReluLayer

Clipped Rectified Linear Unit (ReLU) layer

Description

A clipped ReLU layer performs a threshold operation, where any input value less than zero is set to zero and any value above the clipping ceiling is set to that clipping ceiling.

This operation is equivalent to:

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

This clipping prevents the output from becoming too large.

Creation

Syntax

layer = clippedReluLayer(ceiling)

layer = clippedReluLayer(ceiling,'Name',Name)

Description

layer = clippedReluLayer(ceiling) returns a clipped ReLU layer with the clipping ceiling equal to ceiling.

layer = clippedReluLayer(ceiling,'Name',Name) sets the optional Name property.

Properties

Clipped ReLU

Ceiling — Ceiling for input clipping

positive scalar

Ceiling for input clipping, specified as a positive scalar.

Example: 10

Layer

Name — Layer name

"" (default) | character vector | string scalar

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

The ClippedReLULayer 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 Clipped ReLU Layer

Create a clipped ReLU layer with the name clip1 and the clipping ceiling equal to 10.

layer = clippedReluLayer(10,Name="clip1")

layer = 
  ClippedReLULayer with properties:

       Name: 'clip1'

   Hyperparameters
    Ceiling: 10

Include a clipped ReLU layer in a Layer array.

layers = [ ...
    imageInputLayer([28 28 1])
    convolution2dLayer(5,20)
    clippedReluLayer(10)
    maxPooling2dLayer(2,Stride=2)
    fullyConnectedLayer(10)
    softmaxLayer]

layers = 
  6x1 Layer array with layers:

     1   ''   Image Input       28x28x1 images with 'zerocenter' normalization
     2   ''   2-D Convolution   20 5x5 convolutions with stride [1  1] and padding [0  0  0  0]
     3   ''   Clipped ReLU      Clipped ReLU with ceiling 10
     4   ''   2-D Max Pooling   2x2 max pooling with stride [2  2] and padding [0  0  0  0]
     5   ''   Fully Connected   10 fully connected layer
     6   ''   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, 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, can be described as having the format "SSCB" (spatial, spatial, channel, batch).

ClippedReLULayer 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] Hannun, Awni, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, et al. "Deep speech: Scaling up end-to-end speech recognition." Preprint, submitted 17 Dec 2014. http://arxiv.org/abs/1412.5567

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