Class LayerDimlp3

Inheritance Relationships

Base Type

Class Documentation

class LayerDimlp3 : public Layer

The LayerDimlp3 class represents a Dimlp layer in a neural network using a staircase activation function.

This class inherits from the Layer class and overrides several functions to implement specific behaviors for the forward pass, weight adaptation, and delta computation.

Public Functions

LayerDimlp3(float eta, float mu, float flat, int nbDown, int nbUp, int nbWeights, int nbWeightsForInit, int nbKnots)

Constructs a LayerDimlp3 object with the given parameters.

Initializes the layer with the specified parameters and sets up the staircase activation function.

Parameters:
  • eta – Learning rate.

  • mu – Momentum.

  • flat – Flat spot elimination parameter.

  • nbDown – Number of neurons in the downstream layer.

  • nbUp – Number of neurons in the upstream layer.

  • nbWeights – Number of weights.

  • nbWeightsForInit – Number of weights for initialization.

  • nbKnots – Number of knots for the staircase function.