Package com.jml.neural_network.layers.initilizers

package com.jml.neural_network.layers.initilizers

A package containing an interface for specifying a layer parameter initializer. Also includes various built-in initializers. These initializers can be used to set the staring values of the weights / bias terms (or any other trainable parameters in the layer) before training.

Interface Summary

Interface	Description
Initializer	Interface for bias/weight initialization.

Class Summary

Class	Description
Constant	layer parameter initializer to produce a constant value.
GlorotNormal	{layer parameter initializer to produce random values from a truncated normal distribution with standard deviation std = sqrt(2 / (fanIn + fanOut)) and mean of 0 where fanIn is the input dimension for the layer and fanOut is the output dimension for the layer.
GlorotUniform	layer parameter initializer to produce random values from a clipped uniform distribution in [-lim, lim] where lim = sqrt(6 / (fanIn + fanOut)), fanIn is the input dimension for the layer, and fanOut is the output dimension for the layer.
HeNormal	layer parameter initializer to produce random values from a normal distribution with standard deviation std = sqrt(2 / fanIn) and mean of 0 where fanIn is the input dimension for the layer.
HeUniform	layer parameter initializer to produce random values from a clipped uniform distribution in [-lim, lim] where lim = sqrt(6 / fanIn), fanIn is the input dimension for the layer.
Ones	layer parameter initializer to produce ones.
Orthogonal	layer parameter initializer to produce random orthogonal matrix.
RandomNormal	layer parameter initializer to produce random values from a normal distribution.
RandomUniform	layer parameter initializer to produce random values from a uniform distribution.
Zeros	layer parameter initializer to produce zeros.