Package org.apache.commons.math3.ml.neuralnet

Class FeatureInitializerFactory

java.lang.Object
org.apache.commons.math3.ml.neuralnet.FeatureInitializerFactory
public class FeatureInitializerFactory extends Object
Creates functions that will select the initial values of a neuron's features.
Since:
3.3

  • Method Details

    • uniform

      public static FeatureInitializer uniform(RandomGenerator rng, double min, double max)
      Uniform sampling of the given range.
      Parameters:
      rng - Random number generator used to draw samples from a uniform distribution.
      min - Lower bound of the range.
      max - Upper bound of the range.
      Returns:
      an initializer such that the features will be initialized with values within the given range.
      Throws:
      NumberIsTooLargeException - if min >= max.

    • uniform

      public static FeatureInitializer uniform(double min, double max)
      Uniform sampling of the given range.
      Parameters:
      min - Lower bound of the range.
      max - Upper bound of the range.
      Returns:
      an initializer such that the features will be initialized with values within the given range.
      Throws:
      NumberIsTooLargeException - if min >= max.

    • function

      public static FeatureInitializer function(UnivariateFunction f, double init, double inc)
      Creates an initializer from a univariate function f(x). The argument x is set to init at the first call and will be incremented at each call.
      Parameters:
      f - Function.
      init - Initial value.
      inc - Increment
      Returns:
      the initializer.

    • randomize

      public static FeatureInitializer randomize(RealDistribution random, FeatureInitializer orig)
      Adds some amount of random data to the given initializer.
      Parameters:
      random - Random variable distribution.
      orig - Original initializer.
      Returns:
      an initializer whose value method will return orig.value() + random.sample().