A High Performance SOFM Hardware-System

Rüping S, Porrmann M, Rückert U (1997)
In: Proceedings of the International Work-Conference on Artificial and Natural Neural Networks (IWANN´97). Lanzarote, Spain: 772-781.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
OA
Autor/in
Abstract / Bemerkung
Many applications of Selforganizing Feature Maps (SOFMs) need a high performance hardware system in order to be efficient. Because of the regular and modular structure of SOFMs, a hardware realization is obvious. Based on the idea of a massively parallel system, several chips have been designed, manufactured and tested by the authors. In this paper a high performance system with the latest NBISOM_25 chips is presented. The NBISOM_25 integrated circuit contains 25 processing elements in a 5 by 5 array. Due to the scalability of the chips a VME-bus board was built with 16 ICs on it. The controller for the VME-bus and the SOFM hardware are realized using FPGAs. The system runs SOFM applications with up to 400 elements in parallel mode (20 by 20 map). Each weight vector can have up to 64 weights of 8 bit accuracy. The maximum performance of the board-system is 4.1 GCPS (recall) and 2.4 GCUPS (learning).
Erscheinungsjahr
1997
Titel des Konferenzbandes
Proceedings of the International Work-Conference on Artificial and Natural Neural Networks (IWANN´97)
Seite(n)
772-781
Page URI
https://pub.uni-bielefeld.de/record/2286384

Zitieren

Rüping S, Porrmann M, Rückert U. A High Performance SOFM Hardware-System. In: Proceedings of the International Work-Conference on Artificial and Natural Neural Networks (IWANN´97). Lanzarote, Spain; 1997: 772-781.
Rüping, S., Porrmann, M., & Rückert, U. (1997). A High Performance SOFM Hardware-System. Proceedings of the International Work-Conference on Artificial and Natural Neural Networks (IWANN´97), 772-781. Lanzarote, Spain.
Rüping, S., Porrmann, M., and Rückert, U. (1997). “A High Performance SOFM Hardware-System” in Proceedings of the International Work-Conference on Artificial and Natural Neural Networks (IWANN´97) (Lanzarote, Spain), 772-781.
Rüping, S., Porrmann, M., & Rückert, U., 1997. A High Performance SOFM Hardware-System. In Proceedings of the International Work-Conference on Artificial and Natural Neural Networks (IWANN´97). Lanzarote, Spain, pp. 772-781.
S. Rüping, M. Porrmann, and U. Rückert, “A High Performance SOFM Hardware-System”, Proceedings of the International Work-Conference on Artificial and Natural Neural Networks (IWANN´97), Lanzarote, Spain: 1997, pp.772-781.
Rüping, S., Porrmann, M., Rückert, U.: A High Performance SOFM Hardware-System. Proceedings of the International Work-Conference on Artificial and Natural Neural Networks (IWANN´97). p. 772-781. Lanzarote, Spain (1997).
Rüping, Stefan, Porrmann, Mario, and Rückert, Ulrich. “A High Performance SOFM Hardware-System”. Proceedings of the International Work-Conference on Artificial and Natural Neural Networks (IWANN´97). Lanzarote, Spain, 1997. 772-781.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T08:57:35Z
MD5 Prüfsumme
7d0598974b529f05ca6eed984d26f5a5

Link(s) zu Volltext(en)
Access Level
Restricted Closed Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar