Uses of Class
deepnetts.net.layers.AbstractLayer

Packages that use AbstractLayer

Package	Description
deepnetts.cudnn
deepnetts.net	Neural network architectures with their corresponding builders.
deepnetts.net.layers	Neural network layers, which are main building blocks of a neural network.
deepnetts.net.train.opt	Optimization methods used by training algorithm.

Uses of AbstractLayer in deepnetts.cudnn

Constructors in deepnetts.cudnn with parameters of type AbstractLayer

Modifier	Constructor	Description
	AbstractBackwardCuda(CudaHandles cudaHandles, AbstractLayer layer)
	AbstractForwardCuda(CudaHandles cudaHandles, AbstractLayer layer)
	FlattenForwardCuda(CudaHandles cudaHandles, AbstractLayer layer)

Uses of AbstractLayer in deepnetts.net

Methods in deepnetts.net that return AbstractLayer

Modifier and Type	Method	Description
AbstractLayer	NeuralNetwork.getLayerAt(int idx)

Methods in deepnetts.net that return types with arguments of type AbstractLayer

Modifier and Type	Method	Description
List<AbstractLayer>	NeuralNetwork.getLayers()	Gets layers of this neural network.

Methods in deepnetts.net with parameters of type AbstractLayer

Modifier and Type	Method	Description
ConvolutionalNetwork.Builder	ConvolutionalNetwork.Builder.addLayer(AbstractLayer layer)	Adds a given layer to the network.
FeedForwardNetwork.Builder	FeedForwardNetwork.Builder.addLayer(AbstractLayer layer)	Adds custom layer to this network (which inherits from AbstractLayer)

Uses of AbstractLayer in deepnetts.net.layers

Subclasses of AbstractLayer in deepnetts.net.layers

Modifier and Type	Class	Description
final class	ConvolutionalLayer	Convolutional layer performs image convolution operation on outputs of a previous layer using filters.
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.
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	SoftmaxOutputLayer	Output layer with softmax activation function.

Methods in deepnetts.net.layers that return AbstractLayer

Modifier and Type	Method	Description
AbstractLayer	AbstractLayer.getNextLayer()
AbstractLayer	AbstractLayer.getPrevlayer()

Methods in deepnetts.net.layers with parameters of type AbstractLayer

Modifier and Type	Method	Description
void	AbstractLayer.setNextlayer(AbstractLayer nextlayer)
void	AbstractLayer.setPrevLayer(AbstractLayer prevLayer)

Uses of AbstractLayer in deepnetts.net.train.opt

Methods in deepnetts.net.train.opt with parameters of type AbstractLayer

Modifier and Type	Method	Description
static Optimizer	Optimizer.create(OptimizerType type, AbstractLayer layer)	Factory method to create different types of optimizers

Constructors in deepnetts.net.train.opt with parameters of type AbstractLayer

Modifier	Constructor	Description
	AbstractOptimizer(AbstractLayer layer)
	AdaDeltaOptimizer(AbstractLayer layer)
	AdaGradOptimizer(AbstractLayer layer)
	AdamOptimizer(AbstractLayer layer)
	MomentumOptimizer(AbstractLayer layer)
	RmsPropOptimizer(AbstractLayer layer)
	SgdOptimizer(AbstractLayer layer)