org.cognity.neural.net

Interface FeedforwardNet

All Superinterfaces:

NeuralNet

All Known Implementing Classes:

AbstractFeedforwardNet, MlpNet

public interface FeedforwardNet
extends NeuralNet

A feedforward neural network is a neural network where connections between the units do not form a directed cycle. Layers in such networks are connected in a flat chain.

The following image illustrates a typical feedforward architecture:

All networks that implement this interface should strictly stick to this architecture.

Author:

Artur Markiewicz

Method Summary

Methods

Modifier and Type	Method and Description
List<Layer>	getOrderedLayers() Returns a list of all layers in the network.

Methods inherited from interface org.cognity.neural.net.NeuralNet

compute, getInputLayer, getInputLinks, getInputSize, getLayerCount, getLayers, getLinks, getOneInputLink, getOneOutputLink, getOutputLayer, getOutputLinks, getOutputSize, hasInputLinks, hasOutputLinks

Method Detail

getOrderedLayers

List<Layer> getOrderedLayers()

Returns a list of all layers in the network. The order of layers in the list corresponds to the topological order of layers. I.e. layers are sorted from the input layer to the output layer.

Returns:

a list of all layers in the network