METRICA, l’archivio istituzionale della produzione scientifica dell’Istituto Nazionale di Ricerca Metrologica, ha lo scopo di raccogliere, documentare, conservare e pubblicare, anche ad accesso aperto, i prodotti della ricerca dell’Ente.
METRICA utilizza la piattaforma IRIS (Institutional Research Information System) sviluppata da Cineca.
EnglishThe challenge of developing an efficient artificial neuron is impeded by the use of external CMOS circuits to perform leaking and lateral inhibition. The proposed leaky integrate-and-fire neuron based on the three terminal magnetic tunnel junction (3T-MTJ) performs integration by pushing its domain wall (DW) with spin-transfer or spin-orbit torque. The leaking capability is achieved by pushing the neurons’ DWs in the direction opposite of integration using a stray field from a hard ferromagnet or a non-uniform energy landscape resulting from shape or anisotropy variation. Firing is performed by the MTJ stack. Finally, analog lateral inhibition is achieved by dipolar field repulsive coupling from each neuron. An integrating neuron thus pushes slower neighboring neurons’ DWs in the direction opposite of integration. Applying this lateral inhibition to a ten-neuron output layer within a neuromorphic crossbar structure enables the identification of handwritten digits with 94% accuracy.
Magnetic domain wall neuron with intrinsic leaking and lateral inhibition capability / Brigner, Wesley H.; Hassan, Naimul; Hu, Xuan; Jiang-Wei, Lucian; Akinola, Otitoaleke G.; Garcia-Sanchez, Felipe; Pasquale, Massimo; Bennett, Christopher H.; Incorvia, Jean Anne C.; Friedman, Joseph S.. - Proc. SPIE 11090, Spintronics XII, 1109001 (19 September 2019); doi: 10.1117/12.2551338(2019), p. 128. ((Intervento presentato al convegno SPIE Nanoscience + Engineering, 2019, San Diego tenutosi a California, United States [10.1117/12.2528218].
| Titolo: | Magnetic domain wall neuron with intrinsic leaking and lateral inhibition capability | |
| Autori: | ||
| Data di pubblicazione: | 2019 | |
| Nome del convegno: | SPIE Nanoscience + Engineering, 2019, San Diego | |
| Luogo del convegno: | California, United States | |
| Digital Object Identifier (DOI): | http://dx.doi.org/10.1117/12.2528218 | |
| Abstract: | The challenge of developing an efficient artificial neuron is impeded by the use of external CMOS... circuits to perform leaking and lateral inhibition. The proposed leaky integrate-and-fire neuron based on the three terminal magnetic tunnel junction (3T-MTJ) performs integration by pushing its domain wall (DW) with spin-transfer or spin-orbit torque. The leaking capability is achieved by pushing the neurons’ DWs in the direction opposite of integration using a stray field from a hard ferromagnet or a non-uniform energy landscape resulting from shape or anisotropy variation. Firing is performed by the MTJ stack. Finally, analog lateral inhibition is achieved by dipolar field repulsive coupling from each neuron. An integrating neuron thus pushes slower neighboring neurons’ DWs in the direction opposite of integration. Applying this lateral inhibition to a ten-neuron output layer within a neuromorphic crossbar structure enables the identification of handwritten digits with 94% accuracy. | |
| Full-text (pubblici): | restricted | |
| Appare nelle tipologie: | 4.1 Contributo in Atti di convegno |
File in questo prodotto:
| File | Descrizione | Tipologia | Licenza | |
|---|---|---|---|---|
| spie19.pdf | Documento in Pre-print | Non Pubblico - Accesso privato/ristretto | Utenti riconosciuti Richiedi una copia |
http://hdl.handle.net/11696/61573
Copyright © 2021