org.deeplearning4j.nn.conf.distribution

Class TruncatedNormalDistribution

java.lang.Object

org.deeplearning4j.nn.conf.distribution.Distribution

org.deeplearning4j.nn.conf.distribution.TruncatedNormalDistribution

All Implemented Interfaces:

Serializable, Cloneable

public class TruncatedNormalDistribution
extends Distribution

A truncated normal distribution, with 2 parameters: mean and standard deviation
This distribution is a standard normal/Gaussian distribtion, however values are "truncated" in the sense that any values that fall outside the range [mean - 2 * stdev, mean + 2 * stdev] are re-sampled.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
TruncatedNormalDistribution(double mean, double std) Create a truncated normal distribution with the given mean and std

Method Summary

Modifier and Type	Method and Description
String	toString()

Methods inherited from class org.deeplearning4j.nn.conf.distribution.Distribution

clone

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

TruncatedNormalDistribution

public TruncatedNormalDistribution(double mean,
                                   double std)

Create a truncated normal distribution with the given mean and std

Parameters:

mean - the mean

std - the standard deviation

Method Detail

toString

public String toString()

Overrides:

toString in class Object