Package deepnetts.net.layers

package deepnetts.net.layers

Neural network layers, which are main building blocks of a neural network. Every neural network consists of a sequence of layers.

Related Packages

Package	Description
deepnetts.net	Neural network architectures with their corresponding builders.
deepnetts.net.layers.activation	Activation functions for neural network layers.
deepnetts.net.loss	Commonly used loss functions, which are used to calculate error during the training as a difference between predicted and target output.
deepnetts.net.train	Training algorithms and related utilities.
deepnetts.net.weights	Weights randomization techniques, used for initializing layer's internal parameters.

Class	Description
AbstractLayer<I extends TensorBase,O extends TensorBase,W extends TensorBase>	Base class for different types of layers.
ConvolutionalLayer	Convolutional layer performs image convolution operation on outputs of a previous layer using filters.
Filter	Settings of a convolutional filter which is used to learn to detect pixel patterns.
Filters
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.
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.
InputLayer	Input layer in a neural network.
Layer<O extends TensorBase>	Common base interface for all types of neural network layers.
LayerType	Supported types of layers.
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.
OutputLayer	Output layer of a neural network.
SoftmaxOutputLayer	Output layer with softmax activation function.