Immunity to Device Variations in a Spiking Neural Network With Memristive Nanodevices

Memristive nanodevices can feature a compact multilevel nonvolatile memory function, but are prone to device variability. We propose a novel neural network-based computing paradigm, which exploits their specific physics, and which has virtual immunity to their variability. Memristive devices are use...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on nanotechnology 2013-05, Vol.12 (3), p.288-295
Hauptverfasser:	Querlioz, Damien, Bichler, Olivier, Dollfus, Philippe, Gamrat, Christian
Format:	Artikel
Sprache:	eng
Schlagworte:	Applied sciences Biological neural networks Electronic equipment and fabrication. Passive components, printed wiring boards, connectics Electronics Exact sciences and technology Homeostasis Integrated circuits Integrated circuits by function (including memories and processors) Magnetic and optical mass memories Memristive devices memristors Molecular electronics, nanoelectronics Nanoscale devices Neural networks neuromorphic Neurons Performance evaluation Physics Robustness Semiconductor electronics. Microelectronics. Optoelectronics. Solid state devices spike timing dependent plasticity (STPD) spiking neural networks Storage and reproduction of information Studies Synapses unsupervised learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!