An introduction to modular map systems

N. Lightowler, C. T. Spracklen, A. R. Allen

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

Abstract

We present an overview of our design for a fully digital hardware implementation of the Self Organising Map (SOM) (T. Kohonen, 1982). Our approach has resulted in a modular system (Modular Maps) which utilises fine grain parallelism with each neuron being a separate entity implemented as a small RISC processor. The essence of the SOM has been maintained by this design, although minor modifications have been made to the original algorithm to facilitate implementation. Modules can be used as either stand alone systems or combined to enable large networks to be created and large input vectors to be catered for. A simulator system was developed to facilitate investigation into the high level behaviour of Modular Map systems and, as Modular Maps are computationally intensive and parallel in nature, it was implemented on a parallel computer system. A series of simulations was carried out using encoded images of human faces where it was found that the classification accuracy of a Modular Map system offered an improvement over that of the traditional SOM
Original languageEnglish
Title of host publicationNeural and Fuzzy Systems: Design, Hardware and Applications, Colloquium Digest 1997/133
PublisherIEE
Pages3/1-3/4
Number of pages4
Volume1997/133
Edition133
DOIs
Publication statusPublished - 1997

Publication series

NameColloqium Digest
PublisherIEE
Number133
Volume1997
ISSN (Print)0963-3308

Fingerprint

Dive into the research topics of 'An introduction to modular map systems'. Together they form a unique fingerprint.

Cite this