Package org.tribuo.math

package org.tribuo.math

Contains the implementation of Tribuo's math library, it's gradient descent optimisers, kernels and a set of math related utils.

This package contains two core interfaces for Tribuo's gradient descent system, Parameters which controls how parameters updated via gradient descent are accessed, and StochasticGradientOptimiser which provides the optimisation interface.

Related Packages

Package	Description
org.tribuo	Provides the core interfaces and classes for using Tribuo.
org.tribuo.math.distance	An interface for distance computations between two SGDVector instances along with some standard implementations.
org.tribuo.math.distributions	A package of statistical distributions.
org.tribuo.math.kernel	Provides a Kernel interface for Mercer kernels, along with implementations of standard kernels.
org.tribuo.math.la	Provides a linear algebra system used for numerical operations in Tribuo.
org.tribuo.math.neighbour	Provides nearest neighbour query functionality.
org.tribuo.math.onnx	Utilities for converting Tribuo math objects into ONNX representations.
org.tribuo.math.optimisers	Provides implementations of StochasticGradientOptimiser.
org.tribuo.math.util	Provides math related util classes.

Class	Description
FeedForwardParameters	A Parameters for models which make a single prediction like logistic regressions and neural networks.
LinearParameters	A Parameters for producing linear models.
Parameters	An interface to a Tensor[] array which accepts updates to the parameters.
StochasticGradientOptimiser	Interface for gradient based optimisation methods.