Package com.jml.neural_network.layers.initilizers

Class RandomNormal

java.lang.Object
com.jml.neural_network.layers.initilizers.RandomNormal
All Implemented Interfaces:
Initializer
public class RandomNormal extends Object implements Initializer
layer parameter initializer to produce random values from a normal distribution.

  • Constructor Summary

    Constructors
    Constructor
    Description
    RandomNormal()
    Creates a RandomNormal initializer with mean 0 and standard deviation 1.
    RandomNormal​(double std)
    Creates a RandomNormal initializer with mean 0 and specified standard deviation.
    RandomNormal​(double std, double mean)
    Creates a RandomNormal initializer with specified mean and standard deviation.
    RandomNormal​(double std, double mean, long seed)
    Creates a RandomNormal initializer with specified mean and standard deviation.

  • Method Summary

    Modifier and Type
    Method
    Description
    linalg.Matrix
    init​(int m, int n)
    Creates and initializes a matrix with entries from a Random Normal Distribution.

    Methods inherited from class java.lang.Object

    equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

  • Constructor Details

    • RandomNormal

      public RandomNormal()
      Creates a RandomNormal initializer with mean 0 and standard deviation 1.

    • RandomNormal

      public RandomNormal​(double std)
      Creates a RandomNormal initializer with mean 0 and specified standard deviation.
      Parameters:
      std - Standard deviation for random normal distribution.

    • RandomNormal

      public RandomNormal​(double std, double mean)
      Creates a RandomNormal initializer with specified mean and standard deviation.
      Parameters:
      std - Standard deviation for random normal distribution.
      mean - Mean for random normal distribution.

    • RandomNormal

      public RandomNormal​(double std, double mean, long seed)
      Creates a RandomNormal initializer with specified mean and standard deviation.
      Parameters:
      std - Standard deviation for random normal distribution.
      mean - Mean for random normal distribution.
      seed - Seed for the random number generator.

  • Method Details

    • init

      public linalg.Matrix init​(int m, int n)
      Creates and initializes a matrix with entries from a Random Normal Distribution.
      Specified by:
      init in interface Initializer
      Parameters:
      m - Number of rows in the matrix to initialize.
      n - Number of columns in the matrix.
      Returns: