[This is preliminary documentation and is subject to change.]

This class implements a 3-layer backpropagation neural network in the CLARION Library

The BPNetwork..::..BPNetworkParameters type exposes the following members.

Constructors

  Name Description
Public method BPNetwork..::..BPNetworkParameters(Boolean)
Initializes a parameters class for a BPNetwork
Public method BPNetwork..::..BPNetworkParameters(BPNetwork..::..BPNetworkParameters, Boolean)
Initializes a parameters class for a BPNetwork and sets the values of the parameters to the values specified

Methods

  Name Description
Protected method Global_OnParameterChanged
The event method used for performing global parameter changes
(Inherited from ClarionComponent..::..ClarionComponentParameters.)

Properties

  Name Description
Public property ELIGIBILITY
A switch that can be used to specify eligibility (in the absence of a more sophisticated eligibility method)
Public property INITIAL_THRESHOLDS_LOWER_BOUND
The low bound for the initial threshold
Public property INITIAL_THRESHOLDS_UPPER_BOUND
The upper bound for the initial threshold
Public property INITIAL_WEIGHTS_LOWER_BOUND
The low bound for the initial weights
Public property INITIAL_WEIGHTS_UPPER_BOUND
The upper bound for the initial weights
Protected property IsGlobal
Used to specify whether the particular instance of the parameters class is being used for global or local parameters
(Inherited from ClarionComponent..::..ClarionComponentParameters.)
Public property LEARNING_RATE
The learning rate (used for learning)
Public property MOMENTUM
The momentum (used for learning)
Public property R_ZERO
The error tolerance (used for learning)

See Also