Memristor-based neural networks: Synaptic versus neuronal stochasticity

Rawan Naous, Maruan Alshedivat, Emre Neftci, Gert Cauwenberghs, Khaled N. Salama

Research output: Contribution to journalArticlepeer-review

34 Scopus citations

Abstract

In neuromorphic circuits, stochasticity in the cortex can be mapped into the synaptic or neuronal components. The hardware emulation of these stochastic neural networks are currently being extensively studied using resistive memories or memristors. The ionic process involved in the underlying switching behavior of the memristive elements is considered as the main source of stochasticity of its operation. Building on its inherent variability, the memristor is incorporated into abstract models of stochastic neurons and synapses. Two approaches of stochastic neural networks are investigated. Aside from the size and area perspective, the impact on the system performance, in terms of accuracy, recognition rates, and learning, among these two approaches and where the memristor would fall into place are the main comparison points to be considered.
Original languageEnglish (US)
Pages (from-to)111304
JournalAIP Advances
Volume6
Issue number11
DOIs
StatePublished - Nov 2 2016

Fingerprint

Dive into the research topics of 'Memristor-based neural networks: Synaptic versus neuronal stochasticity'. Together they form a unique fingerprint.

Cite this