Uses of Interface
jsat.classifiers.neuralnetwork.activations.ActivationLayer

Packages that use ActivationLayer

Package	Description
jsat.classifiers.neuralnetwork
jsat.classifiers.neuralnetwork.activations

Uses of ActivationLayer in jsat.classifiers.neuralnetwork

Method parameters in jsat.classifiers.neuralnetwork with type arguments of type ActivationLayer

Modifier and Type	Method and Description
void	SGDNetworkTrainer.setLayersActivation(List<ActivationLayer> layersActivation) Sets the list of layer activations for all layers other than the input layer.

Uses of ActivationLayer in jsat.classifiers.neuralnetwork.activations

Classes in jsat.classifiers.neuralnetwork.activations that implement ActivationLayer

Modifier and Type	Class and Description
class	LinearLayer
class	ReLU This Activation Layer is for Rectified Linear Units.
class	SigmoidLayer This layer provides the standard Sigmoid activation f(x) = 1/(1+exp(-x))
class	SoftmaxLayer This activation layer is meant to be used as the top-most layer for classification problems, and uses the softmax function (also known as cross entropy) to convert the inputs into probabilities.
class	SoftSignLayer This provides the Soft Sign activation function f(x) = x/(1+abs(x)), which is similar to the tanh activation and has a min/max of -1 and 1.
class	TanhLayer This layer provides the standard tanh activation f(x) = tanh(x)

Methods in jsat.classifiers.neuralnetwork.activations that return ActivationLayer

Modifier and Type	Method and Description
ActivationLayer	ActivationLayer.clone()