Package org.deeplearning4j.nn.layers

Class Summary

Class	Description
AbstractLayer<LayerConfT extends Layer>	A layer with input and output, no parameters or gradients
ActivationLayer	Activation Layer Used to apply activation on input and corresponding derivative on epsilon.
BaseLayer<LayerConfT extends BaseLayer>	A layer with parameters
BaseOutputLayer<LayerConfT extends BaseOutputLayer>	Output layer with different objective in co-occurrences for different objectives.
BasePretrainNetwork<LayerConfT extends BasePretrainNetwork>	Baseline class for any Neural Network used as a layer in a deep network *
DropoutLayer	Created by davekale on 12/7/16.
FrozenLayer	For purposes of transfer learning A frozen layers wraps another dl4j layer within it.
FrozenLayerWithBackprop	Frozen layer freezes parameters of the layer it wraps, but allows the backpropagation to continue.
LossLayer	LossLayer is a flexible output "layer" that performs a loss function on an input without MLP logic.
OutputLayer	Output layer with different objective incooccurrences for different objectives.