C# Class numl.Supervised.NeuralNetwork.NetworkLayer

An independent Neural Network layer for use in constructing deep neural networks with ensembles, etc.
Inheritance: numl.Supervised.NeuralNetwork.Network
Show file Open project: sethjuarez/numl

Public Methods

Method Description
NetworkLayer ( int inputNodes, int outputNodes, bool isFullyConnected, int hiddenLayers, Func fnNodeInitializer, bool isAutoencoder = false, int layerConnections = null, bool createBiasNodes = true, bool linkBiasNodes = true ) : System

Initializes a new Network Layer. A network layer is sub neural network made up of inputs, hidden layer(s) and an output layer.

Method Details

NetworkLayer() public method

Initializes a new Network Layer. A network layer is sub neural network made up of inputs, hidden layer(s) and an output layer.
public NetworkLayer ( int inputNodes, int outputNodes, bool isFullyConnected, int hiddenLayers, Func fnNodeInitializer, bool isAutoencoder = false, int layerConnections = null, bool createBiasNodes = true, bool linkBiasNodes = true ) : System
inputNodes int Number of Nodes at the input layer (includes bias Node).
outputNodes int Number of Nodes at the output layer.
isFullyConnected bool Indicates whether the output layer of this network is fully connected with the next Network Layer / Network.
hiddenLayers int Number of Nodes in each layer and the number of layers, where the array length is the number of /// layers and each value is the number of Nodes in that layer.
fnNodeInitializer Func Function for creating a new Node at each layer (zero-based) and Node index (zero-based). The 0 index layer corresponds to the input layer.
isAutoencoder bool Determines whether this Network layer is an auto-encoding layer.
layerConnections int (Optional) Connection properties for this Network where the first dimension is the layer, second the Node index in that layer, /// and third the Node indexes in the next layer to pair with.For example: 1 => 2 => [2, 3] will link Node 2 in layer 1 to Nodes 2 + 3 in layer 2.
createBiasNodes bool (Optional) Indicates whether bias nodes are automatically created (thus bypassing the function).
linkBiasNodes bool (Optional) Indicates whether bias nodes in hidden layers are automatically linked to their respective hidden nodes. /// If this is set to True, it will override any bias node connections specified in parameter
return System