Interface | Description |
---|---|
Randomizer |
Defines the interface for a class that is capable of randomizing the weights
and bias values of a neural network.
|
Class | Description |
---|---|
BasicRandomizer |
Provides basic functionality that most randomizers will need.
|
ConsistentRandomizer |
A randomizer that takes a seed and will always produce consistent results.
|
ConstRandomizer |
A randomizer that will create always set the random number to a const value,
used mainly for testing.
|
Distort |
A randomizer that distorts what is already present in the neural network.
|
FanInRandomizer |
A randomizer that attempts to create starting weight values that are
conducive to propagation training.
|
GaussianRandomizer |
Generally, you will not want to use this randomizer as a pure neural network
randomizer.
|
NguyenWidrowRandomizer |
Implementation of Nguyen-Widrow weight initialization.
|
RandomChoice |
Generate random choices unevenly.
|
RangeRandomizer |
A randomizer that will create random weight and bias values that are between
a specified range.
|
Copyright © 2014. All Rights Reserved.