| FeedForwardNetwork Class |
Inheritance HierarchyNamespace: Imsl.DataMining.Neural
Assembly: ImslCS (in ImslCS.dll) Version: 6.5.2.0
SyntaxThe FeedForwardNetwork type exposes the following members.
Constructors| Name | Description | |
|---|---|---|
 | FeedForwardNetwork |
Creates a new instance of FeedForwardNetwork.
|
Methods| Name | Description | |
|---|---|---|
| ComputeStatistics |
Computes error statistics.
(Inherited from Network.) |
| CreateHiddenLayer |
Creates a HiddenLayer.
(Overrides NetworkCreateHiddenLayer.) |
| Equals | Determines whether the specified object is equal to the current object. (Inherited from Object.) |
 | Finalize | Allows an object to try to free resources and perform other cleanup operations before it is reclaimed by garbage collection. (Inherited from Object.) |
| FindLink |
Returns the Link between two Nodes.
|
| FindLinks |
Returns all of the Links to a given Node.
|
| Forecast |
Computes a forecast using the Network.
(Overrides NetworkForecast(Double).) |
| GetForecastGradient |
Returns the derivatives of the outputs with respect to the
weights.
(Overrides NetworkGetForecastGradient(Double).) |
| GetHashCode | Serves as a hash function for a particular type. (Inherited from Object.) |
| GetType | Gets the Type of the current instance. (Inherited from Object.) |
| Link(Node, Node) |
Establishes a Link between two Nodes.
|
| Link(Node, Node, Double) | |
| LinkAll |
For each Layer in the Network,
link each Node in the
Layer to each Node in the next Layer.
|
| LinkAll(Layer, Layer) |
Links all of the Nodes in one Layer
to all of the Nodes in another Layer.
|
| MemberwiseClone | Creates a shallow copy of the current Object. (Inherited from Object.) |
| Remove |
Removes a Link from the Network.
|
| SetEqualWeights |
Initializes network weights using equal weighting.
|
| SetRandomWeights |
Initializes network weights using random weights.
|
| ToString | Returns a string that represents the current object. (Inherited from Object.) |
| ValidateLink |
Checks that a Link between two Nodes
is valid.
|
Properties| Name | Description | |
|---|---|---|
 | HiddenLayers |
The HiddenLayers in this Network.
|
| InputLayer |
The InputLayer in this Network.
(Overrides NetworkInputLayer.) |
| Links |
All the Links in this Network.
(Overrides NetworkLinks.) |
| NumberOfInputs |
The number of InputNodes to the Network.
(Overrides NetworkNumberOfInputs.) |
| NumberOfLinks |
The number of Links in the Network.
(Overrides NetworkNumberOfLinks.) |
| NumberOfOutputs |
The number of output Perceptrons from the Network.
(Overrides NetworkNumberOfOutputs.) |
| NumberOfWeights |
The number of weights in the Network.
(Overrides NetworkNumberOfWeights.) |
| OutputLayer |
The neural network OutputLayer.
(Overrides NetworkOutputLayer.) |
| Perceptrons |
The Perceptrons in this Network.
(Overrides NetworkPerceptrons.) |
| Weights |
The weight values for
the Links
in this Network.
(Overrides NetworkWeights.) |
RemarksA Network contains an InputLayer, an OutputLayer and zero or more HiddenLayers. The nullInputLayer and OutputLayer are automatically created by the Network constructor. The InputNodes are added using the InputLayer.CreateInputs(nInputs) method. Output Perceptrons are added using the OutputLayer.CreatePerceptrons(nOutputs) method, and HiddenLayers can be created using the CreateHiddenLayer().CreatePerceptrons(nPerceptrons) method.
The InputLayer contains InputNodes. The HiddenLayers and OutputLayers contain Perceptron nodes. These Nodes are created using factory methods in the Layers.
The Network also contains Links between Nodes. Links are created by methods in this class.
Each Link has a weight and gradient value. Each Perceptron node has a bias value. When the Network is trained, the weight and bias values are used as initial guesses. After the Network is trained the weight, gradient and bias values are set to the values computed by the training.
A feed forward network is a network in which links are only allowed from one layer to a following layer.
See Also