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\left(x\right)=\left\{\begin{array}{ll}0,\hfill & x<0\hfill \\ x,\hfill & 0\le x`

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`.```

example

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

Properties

expand all

Clipped ReLU

Ceiling for input clipping, specified as a positive scalar.

Example: `10`

Layer

Layer name, specified as a character vector or a string scalar. To include a layer in a layer graph, you must specify a nonempty, unique layer name. If you train a series network with the layer and `Name` is set to `''`, then the software automatically assigns a name to the layer at training time.

Data Types: `char` | `string`

Number of inputs of the layer. This layer accepts a single input only.

Data Types: `double`

Input names of the layer. This layer accepts a single input only.

Data Types: `cell`

Number of outputs of the layer. This layer has a single output only.

Data Types: `double`

Output names of the layer. This layer has a single output only.

Data Types: `cell`

Examples

collapse all

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 classificationLayer]```
```layers = 7x1 Layer array with layers: 1 '' Image Input 28x28x1 images with 'zerocenter' normalization 2 '' Convolution 20 5x5 convolutions with stride [1 1] and padding [0 0 0 0] 3 '' Clipped ReLU Clipped ReLU with ceiling 10 4 '' 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 7 '' Classification Output crossentropyex ```

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

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

Introduced in R2017b