In this paper we present the implementation of a successful neurochip, the TotemNC3003 Twinchip by Neuricam, on an FPGA based board lodging the last generation Stratix device from Altera. We already evaluated the performance of the chip in typical neuronal applications, showing that it can outperform a PC, due also to the Reactive Tabu Search algorithm it implements during training and generalising phases. Now, aim of the project is to add a further acceleration degree, by employing a technology which allows to fully integrate the neural algorithm straight onto the hardware and to modify the chip architecture for a more efficient implementation of the neural elaboration.

The Totem neurochip: an FPGA implementation

DANESE, GIOVANNI;BERA, MARCO;LEPORATI, FRANCESCO;SPELGATTI, ALVARO
2004-01-01

Abstract

In this paper we present the implementation of a successful neurochip, the TotemNC3003 Twinchip by Neuricam, on an FPGA based board lodging the last generation Stratix device from Altera. We already evaluated the performance of the chip in typical neuronal applications, showing that it can outperform a PC, due also to the Reactive Tabu Search algorithm it implements during training and generalising phases. Now, aim of the project is to add a further acceleration degree, by employing a technology which allows to fully integrate the neural algorithm straight onto the hardware and to modify the chip architecture for a more efficient implementation of the neural elaboration.
2004
Proc. of ISSPIT - Int. Symp. on Signal Proc. and Inf. Tech.
G. Galati, A. Tantawy, E. Abdel-Raheem, D. Bovet, A. Elmaghraby
Computer Science & Engineering includes resources on computer hardware and architecture, computer software, software engineering and design, computer graphics, programming languages, theoretical computing, computing methodologies, broad computing topics, and interdisciplinary computer applications.
Esperti anonimi
Inglese
contributo
ISSPIT - Int. Symp. on Signal Proc. and Inf. Tech.
Dicembre 2004
Roma
Internazionale
STAMPA
461
464
4
9780780386907
IEEE Computer Society Press
Tematica Ex SIR: Sistemi multiprocessore per reti neurali (Classif. Ex SIR:Atti di convegni internazionali con revisori di livello elevato articolo breve/poster ) Dicembre
Reconfigurable architectures; Neural Networks; Real Time systems; Multiprocessing
none
Avogadro, Matteo; Danese, Giovanni; Bera, Marco; Leporati, Francesco; Spelgatti, Alvaro
273
info:eu-repo/semantics/conferenceObject
5
4 Contributo in Atti di Convegno (Proceeding)::4.1 Contributo in Atti di convegno
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11571/19571
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 2
social impact