Package org.ea.javacnn.layers

Interface Summary

Interface	Description
Layer	A convolution neural network is built of layers that the data traverses back and forth in order to predict what the network sees in the data.

Class Summary

Class	Description
ConvolutionLayer	This layer uses different filters to find attributes of the data that affects the result.
DropoutLayer	This layer will remove some random activations in order to defeat over-fitting.
FullyConnectedLayer	Neurons in a fully connected layer have full connections to all activations in the previous layer, as seen in regular Neural Networks.
InputLayer	The input layer is a simple layer that will pass the data though and create a window into the full training data set.
LocalResponseNormalizationLayer	This layer is useful when we are dealing with ReLU neurons.
MaxoutLayer	Implements Maxout nonlinearity that computes x to max(x) where x is a vector of size group_size.
PoolingLayer	This layer will reduce the dataset by creating a smaller zoomed out version.
RectifiedLinearUnitsLayer	This is a layer of neurons that applies the non-saturating activation function f(x)=max(0,x).
SigmoidLayer	Implements Sigmoid nonlinearity elementwise x to 1/(1+e^(-x)) so the output is between 0 and 1.
TanhLayer	Implements Tanh nonlinearity elementwise x to tanh(x) so the output is between -1 and 1.