Research Area:  Machine Learning
To tackle important combinatorial optimization problems, a variety of annealing-inspired computing accelerators, based on several different technology platforms, have been proposed, including quantum-, optical- and electronics-based approaches. However, to be of use in industrial applications, further improvements in speed and energy efficiency are necessary. Here, we report a memristor-based annealing system that uses an energy-efficient neuromorphic architecture based on a Hopfield neural network. Our analogue–digital computing approach creates an optimization solver in which massively parallel operations are performed in a dense crossbar array that can inject the needed computational noise through the analogue array and device errors, amplified or dampened by using a novel feedback algorithm. We experimentally show that the approach can solve non-deterministic polynomial-time (NP)-hard max-cut problems by harnessing the intrinsic hardware noise. We also use experimentally grounded simulations to explore scalability with problem size, which suggest that our memristor-based approach can offer a solution throughput over four orders of magnitude higher per power consumption relative to current quantum, optical and fully digital approaches.
Keywords:  
Author(s) Name:   Fuxi Cai, Suhas Kumar, Thomas Van Vaerenbergh, Xia Sheng, Rui Liu, Can Li, Zhan Liu, Martin Foltin, Shimeng Yu, Qiangfei Xia, J. Joshua Yang, Raymond Beausoleil, Wei D. Lu & John Paul Strachan
Journal name:  Nature Electronics
Conferrence name:  
Publisher name:  Springer nature
DOI:  10.1038/s41928-020-0436-6
Volume Information:  volume 3, pages 409–418 (2020)
Paper Link:   https://www.nature.com/articles/s41928-020-0436-6