Package lnsc.pmvf

PMVF: Parameterized Multi-variate Vector-valued Function

See:
Description

Interface Summary

FunctionalUnit2

Interface supported by every objects that can be used like a function.

Class Summary

AbstractFunctionalUnit2	Abstract class containing the basic implementation for the FunctionalUnit2 interface.
FastSingleLayerNeuralNetwork	Implements a single layer feed forward network.
FunctionalUnit2.ProcessPatternResult2	Return type for the method FunctionalUnit2.processPattern(double[], boolean, boolean, boolean, boolean, java.lang.String[]).

Package lnsc.pmvf Description

PMVF: Parameterized Multi-variate Vector-valued Function

This package contains the definition of the basic interfaces for a parameterized multi-variate vector-valued function. This is an extension of the original lnsc.FunctionalUnit interface first developed by François Rivest in 1998. This extension exist on paper almost since the original design, but was not implemented at that time to accelerate the early development.

The package also contains numerous parameterized multi-variate vector-valued functions from simple gaussians, sigmoids and the like to complex neural networks. See ...

The code of this library and the conceptual structure of this library are the intellectual property of Francois Rivest. This package was developed for research purpose and any commercial use, and non-educational use is strictly prohibited unless explicit written consent is given by the author Francois Rivest. Copyright 2003-2008.