Novel RAM-based neural networks for object recognition

Howells, Gareth and Fairhurst, Michael and Bisset, D.L. (1996) Novel RAM-based neural networks for object recognition. In: Solomon, Susan S. and Batchelor, Bruce G. and Waltz, Frederick M., eds. Proceedings of the society of photo-optical instrumentation engineers(SPIE). Spie - Int Soc Optical Engineering pp. 50-57. ISBN 0-8194-2310-6. (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided)

The full text of this publication is not available from this repository. (Contact us about this Publication)


This paper introduces a novel networking strategy for RAM-based Neurons which significantly improves the training and recognition performance of such networks whilst maintaining the generalisation capabilities achieved in previous network configurations. A number of different architectures are introduced each using the same underlying principles. Initially, features which are common to all architectures are described illustrating the basis of the underlying paradigm. Three architectures are then introduced illustrating different techniques for employing the paradigm to meet differing performance specifications. The architectures are described in terms of the structure of the neurons they employ. Greater detail of the various training and recognition algorithms employed by the architectures may be found in the referenced papers.

Item Type: Conference or workshop item (Paper)
Additional information: Conference on Machine Vision Applications, Architectures, and Systems Integration V BOSTON, MA, NOV 18-19, 1996 Soc Photo Opt Instrumentat Engineers
Subjects: Q Science > Q Science (General) > Q335 Artificial intelligence
Divisions: Faculties > Science Technology and Medical Studies > School of Engineering and Digital Arts
Depositing User: R.F. Xu
Date Deposited: 04 Jun 2009 16:03
Last Modified: 17 Jun 2014 10:39
Resource URI: (The current URI for this page, for reference purposes)
  • Depositors only (login required):