Kolcz, A. and Allinson, N. M. (1994) Euclidean input mapping in a N-tuple approximation network. In: 1994 Sixth IEEE Digital Signal Processing Workshop, 2-5 October 1994, Yosemite National Park, CA, USA.

PDF 00379821.pdf - Whole Document Restricted to Repository staff only Download (488Kb) | Request a copy

Abstract

A type of the N-tuple neural architecture can be shown to perform function approximation based on local interpolation, similar that performed by RBF networks. Since the size and speed of operation in this implementation are independent of the training set size, it is attractive for practical adaptive solutions. However, the kernel function used by the network is non-Euclidean, which can cause performance losses for high-dimensional input data. The authors investigate methods for realising more isotropic kernel basis functions by use of special data encoding techniques

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	A type of the N-tuple neural architecture can be shown to perform function approximation based on local interpolation, similar that performed by RBF networks. Since the size and speed of operation in this implementation are independent of the training set size, it is attractive for practical adaptive solutions. However, the kernel function used by the network is non-Euclidean, which can cause performance losses for high-dimensional input data. The authors investigate methods for realising more isotropic kernel basis functions by use of special data encoding techniques
Keywords:	N-tuple techniques, neural nets, function approximation, interpolation
Subjects:	G Mathematical and Computer Sciences > G730 Neural Computing
Divisions:	College of Sciences > Faculty of Science > Lincoln School of Computer Science
Depositing User:	Tammie Farley
Date Deposited:	20 Apr 2012 15:48
Last Modified:	13 Mar 2013 09:06
URI:	http://eprints.lincoln.ac.uk/id/eprint/5076

Actions (login required)

View Item