A COprocessor for KOhonen´s self-organizing map (COKOS)

Author

Speckmann, H. ; Thole, P. ; Rosenstiel, W.

Author_Institution

Wilhelm-Schickard-Inst. fur Inf., Tubingen Univ., Germany

Volume

2

fYear

1993

fDate

25-29 Oct. 1993

Firstpage

1951

Abstract

Presents a system which enables easy and fast computation of Kohonen´s self-organizing map (SOM). It is a hardware supported system consisting of different parts. A neural coprocessor (COKOS) is connected to a personal computer (PC) by a special, asynchronous interface. The neural coprocessor works vector-component-parallel and processing-element-serial and speeds up the performance of Kohonen´s algorithm of the self-organizing map by magnitude. A user friendly interface (ULTIKOS) supports the preprocessing of the input data and the control and assessment of the learning process.

Keywords

coprocessors; learning (artificial intelligence); self-organising feature maps; user interfaces; Kohonen´s self organizing map; asynchronous interface; hardware supported system; neural coprocessor; processing-element-serial; user friendly interface; vector-component-parallel; Application software; Coprocessors; Data preprocessing; Hardware; Impulse testing; Microcomputers; Neural networks; Parallel processing; Power transformers; Topology;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on

Print_ISBN

0-7803-1421-2

Type

conf

DOI

10.1109/IJCNN.1993.717038

Filename

717038