Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
ELECTRONIC IMPLEMENTATION OF AN ANALOG ATTRACTOR NEURAL-NETWORK WITH STOCHASTIC LEARNING
Autore:
BADONI D; BERTAZZONI S; BUGLIONI S; SALINA G; AMIT DJ; FUSI S;
Indirizzi:
UNIV ROMA TOR VERGATA,DIPARTIMENTO FIS,INFN,V RIC SCI I I-00133 ROME ITALY HEBREW UNIV JERUSALEM,RACAH INST PHYS JERUSALEM ISRAEL UNIV ROMA LA SAPIENZA,DIPARTIMENTO FIS,INFN I-00185 ROME ITALY IST SUPER SANITA,INFN I-00161 ROME ITALY
Titolo Testata:
Network
fascicolo: 2, volume: 6, anno: 1995,
pagine: 125 - 157
SICI:
0954-898X(1995)6:2<125:EIOAAA>2.0.ZU;2-4
Fonte:
ISI
Lingua:
ENG
Soggetto:
PRIMATE TEMPORAL CORTEX; SHORT-TERM-MEMORY; NEURONAL CORRELATE; UNIT-ACTIVITY; ORGANIZATION; SYNAPSES;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
CompuMath Citation Index
Science Citation Index Expanded
Science Citation Index Expanded
Science Citation Index Expanded
Citazioni:
41
Recensione:
Indirizzi per estratti:
Citazione:
D. Badoni et al., "ELECTRONIC IMPLEMENTATION OF AN ANALOG ATTRACTOR NEURAL-NETWORK WITH STOCHASTIC LEARNING", Network, 6(2), 1995, pp. 125-157

Abstract

We describe and discuss an electronic implementation of an attractor neural network with plastic synapses. The network undergoes double dynamics, for the neurons as well as the synapses. Both dynamical processes are unsupervised. The synaptic dynamics is autonomous, in that it is driven exlusively and perpetually by neural activities. The latter follow the network activity via the developing synapses and the influence of external stimuli. Such a network self-organizes and is a device which converts the gross statistical characteristics of the stimulus input stream into a set of attractors (reverberations). To maintain forlong time the acquired memory, the analog synaptic efficacies are discretized by a stochastic refresh mechanism. The discretized synaptic memory has indefinitely long lifetime in the absence of activity in thenetwork. It is modified only by the arrival of new stimuli. The stochastic refresh mechanism produces transitions at low probability which ensures that transient stimuli do not create significant modificationsand that the system has large palimpsestic memory. A change in the attractor structure represents a major, macroscopic change in the statistics of the input stream, which may deform attractors, may create new ones and may eliminate others. The electronic implementation is completely analogue, stochastic and asynchronous. The circuitry of the firstprototype is discussed in detail as well as the tests performed on it. In carrying out the implementation we have been guided by biologicalconsiderations and by electronic constraints. Both are discussed and new insights and lessons for the learning process are proposed.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 21/09/20 alle ore 18:34:28