Neural Splines Exploiting Parallelism for Function Approximation Using Modular Neural Networks

dc.contributor.author	Lagaris, I. E.	en
dc.contributor.author	Tsoulos, I.	en
dc.contributor.author	Likas, A	en
dc.date.accessioned	2015-11-24T17:01:00Z
dc.date.available	2015-11-24T17:01:00Z
dc.identifier.uri	https://olympias.lib.uoi.gr/jspui/handle/123456789/10855
dc.rights	Default Licence	-
dc.title	Neural Splines Exploiting Parallelism for Function Approximation Using Modular Neural Networks	en
heal.abstract	We introduce the Neural Spline, that is a mathematical model built by combining a neural network and an associated Obreshkov polynomial. The neural spline has nite support and can be used as the basic element in constructing continuous mod- ular neural-based models. These models are suitable for function approximation in partitioned domains and are also amenable to e cient parallel or distributed im- plementation. Experimental results are presented for test problems in one and two dimensions which illustrate the e ectiveness of the proposed function approximation scheme.	en
heal.access	campus	-
heal.fullTextAvailability	TRUE	-
heal.journalName	Neural Parallel and Scientific Computations	en
heal.journalType	peer reviewed	-
heal.language	en	-
heal.publicationDate	2005	-
heal.recordProvider	Πανεπιστήμιο Ιωαννίνων. Σχολή Θετικών Επιστημών. Τμήμα Μηχανικών Ηλεκτρονικών Υπολογιστών και Πληροφορικής	el
heal.type	journalArticle	-
heal.type.el	Άρθρο Περιοδικού	el
heal.type.en	Journal article	en

Αρχεία

Προβολή: 1 - 1 of 1