DeepLearning
Layer
layer object
Description
Generating Layers
Built-in Layers
Compatibility
A Layer is a callable object which takes one or more Tensors as input and output one or more Tensors.
Layers available from DeepLearning encapsulate various types of neural networks. These are typically composed to create a more complex network using the Sequential command.
To construct a Layer object encapsulating a certain task, see the DeepLearning Overview section on Layers.
The following built-in layers are available within DeepLearning.
BatchNormalizationLayer
BidirectionalLayer
ConvolutionLayer
DeconvolutionLayer
DenseLayer
DropoutLayer
EmbeddingLayer
FlattenLayer
GatedRecurrentUnitLayer
LongShortTermMemoryLayer
MaxPoolingLayer
SoftmaxLayer
The DeepLearning[Layer] command was introduced in Maple 2021.
For more information on Maple 2021 changes, see Updates in Maple 2021.
See Also
DeepLearning Overview
Sequential
Download Help Document