INeuralNetwork.SetLearnRadiusEx

Syntax

SetLearnRadiusEx(newLearnRadius: Integer; layerIndex: Integer): Integer;

Parameters

newLearnRadius. Learning step.

layerIndex. Layer index.

Description

The SetLearnRadiusEx method sets a network learning step.

Comments

SetLearnRadiusEx returns value of the previous learning step and is applied only for Kohonen self-organizing maps.

The value of the step can change from zero to the number of neurons in the network. A learning step is a number of neurons around the "winner" that will be shifted and learned. Usually, the learning step tends to zero value towards the end of learning.

Indexation of the layers is continuous and starts with zero.

The method use is given in the example for INeuralNetwork.SetLearnRateEx.