Package org.deeplearning4j.nn.conf.distribution

Class Summary

Class	Description
BinomialDistribution	A binomial distribution, with 2 parameters: number of trials, and probability of success
ConstantDistribution	Constant distribution: a "distribution" where all values are set to the specified constant
Distribution	An abstract distribution.
Distributions	Static methods for instantiating an nd4j distribution from a DL4J distribution configuration object.
GaussianDistribution	Deprecated Use NormalDistribution which is identical to this implementation
LogNormalDistribution	A log-normal distribution, with two parameters: mean and standard deviation.
NormalDistribution	A normal (Gaussian) distribution, with two parameters: mean and standard deviation
OrthogonalDistribution	Orthogonal distribution, with gain parameter. See https://arxiv.org/abs/1312.6120 for details
TruncatedNormalDistribution	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.
UniformDistribution	A uniform distribution, with two parameters: lower and upper - i.e., U(lower,upper)