31 October 1996 Novel RAM-based neural networks for object recognition
Author Affiliations +
Abstract
This paper introduces a novel networking strategy for RAM- based Neurons which significantly improves the training and recognition performance of such networks while maintaining the generalization 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.
© (1996) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Gareth Howells, Gareth Howells, Michael C. Fairhurst, Michael C. Fairhurst, David Bisset, David Bisset, } "Novel RAM-based neural networks for object recognition", Proc. SPIE 2908, Machine Vision Applications, Architectures, and Systems Integration V, (31 October 1996); doi: 10.1117/12.257276; https://doi.org/10.1117/12.257276
PROCEEDINGS
8 PAGES


SHARE
Back to Top