Implementation of the neocognitron on a SIMD architecture

Author

Neveu, J.N.P. ; Kumar, M.J.

Author_Institution

Dept. of Comput. Sci., Curtin Univ. of Technol., Bentley, WA, Australia

fYear

1994

fDate

29 Nov-2 Dec 1994

Firstpage

179

Lastpage

183

Abstract

We consider the implementation of one of the most complex neural networks, the neocognitron, on a SIMD parallel machine. The neocognitron is a network with a heavy cell load and intricate interconnections among its neurons or cells. Its structure is qualitatively similar to the mammalian visual system and its algorithm exhibits data parallelism at several levels. The proposed implementation makes use of an optimal mapping strategy exploring this data parallelism and the communication network of the MasPar Mp12000 SIMD computer

Keywords

neural net architecture; parallel architectures; parallel machines; virtual machines; MasPar Mp12000 SIMD computer; SIMD architecture; SIMD parallel machine; communication network; complex neural networks; data parallelism; heavy cell load; intricate interconnections; mammalian visual system; neocognitron; optimal mapping strategy; Computer architecture; Computer networks; Computer science; Computer simulation; Concurrent computing; Costs; Neural networks; Neurons; Parallel processing; Visual system;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Information Systems,1994. Proceedings of the 1994 Second Australian and New Zealand Conference on

Conference_Location

Brisbane, Qld.

Print_ISBN

0-7803-2404-8

Type

conf

DOI

10.1109/ANZIIS.1994.396925

Filename

396925