Package jsat.classifiers.neuralnetwork.activations

Interface Summary

Interface	Description
ActivationLayer	This interface defines a type of activation layer for use in a Neural Network

Class Summary

Class	Description
LinearLayer
ReLU	This Activation Layer is for Rectified Linear Units.
SigmoidLayer	This layer provides the standard Sigmoid activation f(x) = 1/(1+exp(-x))
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.
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.
TanhLayer	This layer provides the standard tanh activation f(x) = tanh(x)