Arbiter Parameter Spaces

Parameter Spaces


BooleanSpace

[source]

If argument to setValue is less than or equal to 0.5 it will return True else False


FixedValue

[source]

FixedValue is a ParameterSpace that defines only a single fixed value


ContinuousParameterSpace

[source]

getValue
public Double getValue(double[] input) 

ContinuousParameterSpace with uniform distribution between the minimum and maximum values

  • param min Minimum value that can be generated
  • param max Maximum value that can be generated

DiscreteParameterSpace

[source]

A DiscreteParameterSpace is used for a set of un-ordered values


IntegerParameterSpace

[source]

some minimum and maximum value

getMin
public int getMin() 

Create an IntegerParameterSpace with a uniform distribution between the specified min/max (inclusive)

  • param min Min value, inclusive
  • param max Max value, inclusive

MathOp

[source]

A simple parameter space that implements scalar mathematical operations on another parameter space. This allows you to do things like Y = X 2, where X is a parameter space. For example, a layer size hyperparameter could be set using this to 2x the size of the previous layer


PairMathOp

[source]

A simple parameter space that implements pairwise mathematical operations on another parameter space. This allows you to do things like Z = X + Y, where X and Y are parameter spaces.

API Reference

API Reference

Detailed API docs for all libraries including DL4J, ND4J, DataVec, and Arbiter.

Examples

Examples

Explore sample projects and demos for DL4J, ND4J, and DataVec in multiple languages including Java and Kotlin.

Tutorials

Tutorials

Step-by-step tutorials for learning concepts in deep learning while using the DL4J API.

Guide

Guide

In-depth documentation on different scenarios including import, distributed training, early stopping, and GPU setup.

Deploying models? There's a tool for that.