Kolcz, A. and Allinson, N. M. (1995) General memory neural network-extending the properties of basis networks to RAM-based architectures. In: 1995 IEEE International Conference on Neural Networks, 27 Nov - 1 Dec 1995, Perth, WA.

PDF 00488864.pdf - Whole Document Restricted to Repository staff only Download (416Kb) | Request a copy

Abstract

A common framework for architectures combining multiple vector-quantization of the input space with memory look-up operations is proposed. Properties of the model are discussed and, in particular, a close relationship with basis functions networks (such as RBFs and kernel regression networks) is established

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	A common framework for architectures combining multiple vector-quantization of the input space with memory look-up operations is proposed. Properties of the model are discussed and, in particular, a close relationship with basis functions networks (such as RBFs and kernel regression networks) is established
Keywords:	neural networks, neural net architecture, memory architecture, vector quantisation
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 16:18
Last Modified:	13 Mar 2013 09:06
URI:	http://eprints.lincoln.ac.uk/id/eprint/5077

Actions (login required)

View Item