Package com.jml.neural_network.layers.initilizers

Interface Initializer

All Known Implementing Classes:
Constant, GlorotNormal, GlorotUniform, HeNormal, HeUniform, Ones, Orthogonal, RandomNormal, RandomUniform, Zeros
public interface Initializer
Interface for bias/weight initialization. Built-in Initializers: 
     - RandomNormal
     - RandomUniform
     - Zeros
     - Ones
     - Constant
     - GlorotNormal
     - GlorotUniform
     - Orthogonal

  • Method Summary

    Modifier and Type
    Method
    Description
    linalg.Matrix
    init​(int m, int n)
    Initializes values of a weight/bias matrix as specified by this initializer.

  • Method Details

    • init

      linalg.Matrix init​(int m, int n)
      Initializes values of a weight/bias matrix as specified by this initializer.
      Parameters:
      m - Number of rows in the matrix.
      n - Number of columns in the matrix.
      Returns:
      A Matrix initialized with values from the distribution specified by this initializer.