Uses of Interface
deepnetts.net.layers.Forward

Packages that use Forward

Package	Description
deepnetts.accl.spi
deepnetts.net.layers	Neural network layers, which are main building blocks of a neural network.

Uses of Forward in deepnetts.accl.spi

Methods in deepnetts.accl.spi that return Forward

Modifier and Type	Method	Description
Forward	AcceleratorProvider.createConvolutionalForwardAcc(AcceleratorHandle handle, ConvolutionalLayer layer)
Forward	AcceleratorProvider.createFlattenForwardAcc(AcceleratorHandle handle, FlattenLayer layer)
Forward	AcceleratorProvider.createFullyConnectedForwardAcc(AcceleratorHandle handle, FullyConnectedLayer layer)
Forward	AcceleratorProvider.createMaxpoolingForwardAcc(AcceleratorHandle handle, MaxPoolingLayer layer)
Forward	AcceleratorProvider.createOutputForwardAcc(AcceleratorHandle handle, OutputLayer layer)
Forward	AcceleratorProvider.createSoftmaxOutputForwardAcc(AcceleratorHandle handle, SoftmaxOutputLayer layer)

Uses of Forward in deepnetts.net.layers

Subinterfaces of Forward in deepnetts.net.layers

Modifier and Type	Interface	Description
interface	Layer<O extends Tensor>	Common base interface for all types of neural network layers.

Classes in deepnetts.net.layers that implement Forward

Modifier and Type	Class	Description
class	AbstractLayer<I extends TensorBase, O extends TensorBase, W extends TensorBase>	Base class for different types of layers.
class	CBOWEmbeddingLayer
final class	ConvolutionalLayer	Convolutional layer performs image convolution operation on outputs of a previous layer using filters.
class	EmbeddingLayer
class	FlatEmbeddingLayer
class	FlattenLayer	Transforms outputs from previous 3D layer into a flatten 1D tensor in forward pass, Backward pass propagates weighted errors/deltas from the next fully connected layer.
class	FullyConnectedLayer	Fully connected layer is used as a hidden layer in a neural network, and it has a single row of units/nodes/neurons connected to all neurons in previous and next layer.
class	InputLayer	Input layer in a neural network.
class	LayerNorm
final class	MaxPoolingLayer	This layer performs max pooling operation in convolutional neural network, which scales down output from previous layer by taking max outputs from small predefined filter areas.
class	OutputLayer	Output layer of a neural network.
class	SkipGramEmbeddingLayer
class	SoftmaxOutputLayer	Output layer with softmax activation function.

Fields in deepnetts.net.layers declared as Forward

Modifier and Type	Field	Description
protected Forward	AbstractLayer.forwardImpl

Methods in deepnetts.net.layers that return Forward

Modifier and Type	Method	Description
Forward	AbstractLayer.getForwardAcc()