Neuromorphic computing with multi-memristive synapses

Neuromorphic computing has emerged as a promising avenue towards building the next generation of intelligent computing systems. It has been proposed that memristive devices, which exhibit history-dependent conductivity modulation, could efficiently represent the synaptic weights in artificial neural networks. However, precise modulation of the device conductance over a wide dynamic range, necessary to maintain high network accuracy, is proving to be challenging. To address this, we present a multi-memristive synaptic architecture with an efficient global counter-based arbitration scheme. We focus on phase change memory devices, develop a comprehensive model and demonstrate via simulations the effectiveness of the concept for both spiking and non-spiking neural networks. Moreover, we present experimental results involving over a million phase change memory devices for unsupervised learning of temporal correlations using a spiking neural network. The work presents a significant step towards the realization of large-scale and energy-efficient neuromorphic computing systems.

Authors

Irem Boybat; Manuel Le Gallo; S. R. Nandakumar; Timoleon Moraitis; Thomas Parnell; Tomáš Tůma; Bipin Rajendran; Yusuf Leblebici; Abu Sebastian; Evangelos Eleftheriou

Published

Jun 22, 2018

Journal or venue

Nature Communications

DOI

10.1038/s41467-018-04933-y

Paper type

journal article

Source

Openalex