Novel RAM-based neural networks for object recognition

Gareth Howells; Michael C. Fairhurst; David Bisset

doi:10.1117/12.257276

31 October 1996 Novel RAM-based neural networks for object recognition

Gareth Howells, Michael C. Fairhurst, David Bisset

Proceedings Volume 2908, Machine Vision Applications, Architectures, and Systems Integration V; (1996) https://doi.org/10.1117/12.257276
Event: Photonics East '96, 1996, Boston, MA, United States

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.

Citation Download Citation

Gareth Howells, Michael C. Fairhurst, and David Bisset "Novel RAM-based neural networks for object recognition", Proc. SPIE 2908, Machine Vision Applications, Architectures, and Systems Integration V, (31 October 1996); https://doi.org/10.1117/12.257276

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available