Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloExtended memory lifetime in spiking neural networks employing memristive synapses with nonlinear conductance dynamics
Anno di pubblicazione2019
Formato
  • Elettronico
  • Cartaceo
Autore/iBrivio, S.; Conti, D.; Nair, M. V.; Frascaroli, J.; Covi, E.; Ricciardi, C.; Indiveri, G.; Spiga, S.
Affiliazioni autoriCNR--IMM, Unit of Agrate Brianza, Italy; Politecnico di Torino, Dipartimento di Scienza Applicata e Tecnologia (DISAT), Italy; Institute for Neuroinformatics, University of Zürich and ETH Zürich,Zürich, Switzerland.
Autori CNR e affiliazioni
  • JACOPO FRASCAROLI
  • STEFANO BRIVIO
  • ERIKA COVI
  • SABINA SPIGA
Lingua/e
  • inglese
AbstractSpiking neural networks (SNNs) employing memristive synapses are capable of life-long online learning. Because of their ability to process and classify large amounts of data in real-time using compact and low-power electronic systems, they promise a substantial technology breakthrough. However, the critical issue that memristor-based SNNs have to face is the fundamental limitation in their memory capacity due to finite resolution of the synaptic elements, which leads to the replacement of old memories with new ones and to a finite memory lifetime. In this study we demonstrate that the nonlinear conductance dynamics of memristive devices can be exploited to improve the memory lifetime of a network. The network is simulated on the basis of a spiking neuron model of mixed-signal digital-analogue sub-threshold neuromorphic CMOS circuits, and on memristive synapse models derived from the experimental nonlinear conductance dynamics of resistive memory devices when stimulated by trains of identical pulses. The network learning circuits implement a spike-based plasticity rule compatible with both spike-timing and rate-based learning rules. In order to get an insight on the memory lifetime of the network, we analyse the learning dynamics in the context of a classical benchmark of neural network learning, that is hand-written digit classification. In the proposed architecture, the memory lifetime and the performance of the network are improved for memristive synapses with nonlinear dynamics with respect to linear synapses with similar resolution. These results demonstrate the importance of following holistic approaches that combine the study of theoretical learning models with the development of neuromorphic CMOS SNNs with memristive devices used to implement life-long on-chip learning.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da015102-1
Pagine a015102-12
Pagine totali-
RivistaNanotechnology (Bristol. Print)
Attiva dal 1990
Editore: IOP Publishing, - Bristol
Paese di pubblicazione: Regno Unito
Lingua: inglese
ISSN: 0957-4484
Titolo chiave: Nanotechnology (Bristol. Print)
Titolo proprio: Nanotechnology. (Bristol. Print)
Titolo abbreviato: Nanotechnology (Bristol. Print)
Numero volume della rivista30
Fascicolo della rivista1
DOI10.1088/1361-6528/aae81c
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • Scopus (Codice:2-s2.0-85056084486)
  • ISI Web of Science (WOS) (Codice:000448981300001)
  • PubMed (Codice:30378572)
Parole chiavememory lifetime, memristor, ReRAM, spiking neural network, neuromorphic computing, memristice devices, hafnium oxide
Link (URL, URI)https://iopscience.iop.org/article/10.1088/1361-6528/aae81c
Titolo parallelo-
LicenzaCC BY 3.0
Scadenza embargo-
Data di accettazione12/10/2018
Note/Altre informazionionline first: 31 ottobre 2018 Data Pubblicazione Web of Science: 4 Gennaio 2019
Strutture CNR
  • IMM — Istituto per la microelettronica e microsistemi
Moduli/Attività/Sottoprogetti CNR
  • DFM.AD001.081.001 : NEUral computing aRchitectures in Advanced Monolithic 3D-VLSI nano-technologies
Progetti Europei
Allegati
Extended memory lifetime in spiking neural networks employing memristive synapses with nonlinear conductance dynamics (documento privato )
Descrizione: Versione finale pubblicata; open access
Tipo documento: application/pdf