Documentation For Encog 2.x

Encog.Neural.Networks.Training.Competitive.Neighborhood Namespace

Namespace Hierarchy

Classes

Class Description
NeighborhoodBubble A neighborhood function that uses a simple bubble. A width is defined, and any neuron that is plus or minus that width from the winning neuron will be updated as a result of training.
NeighborhoodGaussian A neighborhood function based on the Gaussian function.
NeighborhoodSingle A very simple neighborhood function that will return 1.0 (full effect) for the winning neuron, and 0.0 (no change) for everything else.

Interfaces

Interface Description
INeighborhoodFunction Defines how a neighborhood function should work in competitive training. This is most often used in the training process for a self-organizing map. This function determines to what degree the training should take place on a neuron, based on its proximity to the "winning" neuron.