Harmonic Theory and Machine Learning

A natural inference mechanism is presented : the Black Box problem is transformed into a Dirichlet's problem on the closed cube. Then it is solved in closed polynomial form, together with a Mean-Value theorem and a Maximum Principle.A generalization to Polytopes and a reduction of any Dirichlet...

Full description

Bibliographic Details
Main Authors:	Jorge Nanclares, Ulises Mario Alberto Rapallini
Format:	Article
Language:	English
Published:	Postgraduate Office, School of Computer Science, Universidad Nacional de La Plata 2007-10-01
Series:	Journal of Computer Science and Technology
Subjects:	neural networks machine learning potential theory polynomial approximation
Online Access:	https://journal.info.unlp.edu.ar/JCST/article/view/778

id	doaj-755120ae32f44ea6836399bae03bcab0
record_format	Article
spelling	doaj-755120ae32f44ea6836399bae03bcab02021-05-05T14:01:56ZengPostgraduate Office, School of Computer Science, Universidad Nacional de La PlataJournal of Computer Science and Technology1666-60461666-60382007-10-01703249255472Harmonic Theory and Machine LearningJorge Nanclares0Ulises Mario Alberto Rapallini1Universidad Tecnológica Nacional, Facultad Regional Concepción del Uruguay, GEINAR - Grupo de Estudio en Inteligencia Artificial, Entre Rios, ArgentinaUniversidad Tecnológica Nacional, Facultad Regional Concepción del Uruguay, GEINAR - Grupo de Estudio en Inteligencia Artificial, Entre Rios, ArgentinaA natural inference mechanism is presented : the Black Box problem is transformed into a Dirichlet's problem on the closed cube. Then it is solved in closed polynomial form, together with a Mean-Value theorem and a Maximum Principle.A generalization to Polytopes and a reduction of any Dirichlet problem on compacta is mapp ed into a unit cub e in more dimensions.An algorithm for calculating the solution is suggested.https://journal.info.unlp.edu.ar/JCST/article/view/778neural networksmachine learningpotential theorypolynomial approximation
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Jorge Nanclares Ulises Mario Alberto Rapallini
spellingShingle	Jorge Nanclares Ulises Mario Alberto Rapallini Harmonic Theory and Machine Learning Journal of Computer Science and Technology neural networks machine learning potential theory polynomial approximation
author_facet	Jorge Nanclares Ulises Mario Alberto Rapallini
author_sort	Jorge Nanclares
title	Harmonic Theory and Machine Learning
title_short	Harmonic Theory and Machine Learning
title_full	Harmonic Theory and Machine Learning
title_fullStr	Harmonic Theory and Machine Learning
title_full_unstemmed	Harmonic Theory and Machine Learning
title_sort	harmonic theory and machine learning
publisher	Postgraduate Office, School of Computer Science, Universidad Nacional de La Plata
series	Journal of Computer Science and Technology
issn	1666-6046 1666-6038
publishDate	2007-10-01
description	A natural inference mechanism is presented : the Black Box problem is transformed into a Dirichlet's problem on the closed cube. Then it is solved in closed polynomial form, together with a Mean-Value theorem and a Maximum Principle.A generalization to Polytopes and a reduction of any Dirichlet problem on compacta is mapp ed into a unit cub e in more dimensions.An algorithm for calculating the solution is suggested.
topic	neural networks machine learning potential theory polynomial approximation
url	https://journal.info.unlp.edu.ar/JCST/article/view/778
work_keys_str_mv	AT jorgenanclares harmonictheoryandmachinelearning AT ulisesmarioalbertorapallini harmonictheoryandmachinelearning
_version_	1721460139713626112

Harmonic Theory and Machine Learning

Similar Items