Click or drag to resize
Perceptron Class
A Perceptron node in a neural network.
Inheritance Hierarchy

Namespace: Imsl.DataMining.Neural
Assembly: ImslCS (in ImslCS.dll) Version: 6.5.2.0
Syntax
Copy
[SerializableAttribute]
public class Perceptron : Node

The Perceptron type exposes the following members.

Methods
  NameDescription
Public methodEquals
Determines whether the specified object is equal to the current object.
(Inherited from Object.)
Protected methodFinalize
Allows an object to try to free resources and perform other cleanup operations before it is reclaimed by garbage collection.
(Inherited from Object.)
Public methodGetHashCode
Serves as a hash function for a particular type.
(Inherited from Object.)
Public methodGetType
Gets the Type of the current instance.
(Inherited from Object.)
Public methodGetValue
Returns the value of this Node.
(Inherited from Node.)
Protected methodMemberwiseClone
Creates a shallow copy of the current Object.
(Inherited from Object.)
Public methodSetValue
Sets the value of this Node.
(Inherited from Node.)
Public methodToString
Returns a string that represents the current object.
(Inherited from Object.)
Top
Properties
  NameDescription
Public propertyActivation
The activation function.
Public propertyBias
The bias for this perceptron.
Public propertyLayer
The Layer in which this Node exists.
(Inherited from Node.)
Top
Remarks

Perceptrons are created by factory methods in a Layer. Each Perceptron has an activation function (g) and a bias (\mu). The value of a Perceptron is given by g(\sum_i w_i X_i+\mu), where X_is are the values of nodes input to this Perceptron with weight (w_i).

Network training will use existing bias values for the starting values for the trainer. Upon completion of Network training, the bias values are set to the values computed by the trainer.

See Also