Class LayerFdimlp

Inheritance Relationships

Base Type

Class Documentation

class LayerFdimlp : public Layer

Represents a specialized fuzzy neural network layer using Gaussian activation functions, derived from the Layer class.

This class implements a fuzzy layer in the neural network that uses Gaussian activation functions for its neurons. It overrides specific functions from the base Layer class to provide customized behavior for forward propagation and weight/bias adaptation.

Public Functions

LayerFdimlp(float eta, float mu, float flat, int nbDown, int nbUp, int nbWeights, int nbWeightsForInit)

Constructor for the LayerFdimlp class.

Initializes the layer with the specified parameters.

Parameters:
  • eta – Learning rate.

  • mu – Momentum.

  • flat – Flat spot elimination parameter.

  • nbDown – Number of neurons in the previous layer.

  • nbUp – Number of neurons in the current layer.

  • nbWeights – Total number of weights.

  • nbWeightsForInit – Number of weights for initialization.