Optimising memory usage in n-tuple neural networks

Mitchell, R. J., Bishop, J. M. and Minchinton, P. R. (1996) Optimising memory usage in n-tuple neural networks. Mathematics and Computers in Simulation, 40 (5-6). pp. 549-563. ISSN 0378-4754 doi: 10.1016/0378-4754(95)00006-2

Abstract/Summary

The use of n-tuple or weightless neural networks as pattern recognition devices is well known (Aleksander and Stonham, 1979). They have some significant advantages over the more common and biologically plausible networks, such as multi-layer perceptrons; for example, n-tuple networks have been used for a variety of tasks, the most popular being real-time pattern recognition, and they can be implemented easily in hardware as they use standard random access memories. In operation, a series of images of an object are shown to the network, each being processed suitably and effectively stored in a memory called a discriminator. Then, when another image is shown to the system, it is processed in a similar manner and the system reports whether it recognises the image; is the image sufficiently similar to one already taught? If the system is to be able to recognise and discriminate between m-objects, then it must contain m-discriminators. This can require a great deal of memory. This paper describes various ways in which memory requirements can be reduced, including a novel method for multiple discriminator n-tuple networks used for pattern recognition. By using this method, the memory normally required to handle m-objects can be used to recognise and discriminate between 2^m — 2 objects.

Item Type	Article
URI	https://reading-clone.eprints-hosting.org/id/eprint/18867
Item Type	Article
Refereed	Yes
Divisions	Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
Uncontrolled Keywords	neural networks, pattern recognition
Publisher	Elsevier
Download/View statistics	View download statistics for this item