Harnessing Intrinsic Noise in Memristor Hopfield Neural Networks for Combinatorial Optimization

TL;DR

This paper introduces a memristor-based Hopfield neural network that exploits intrinsic analog noise for efficient combinatorial optimization, demonstrating high throughput and scalability at room temperature.

Contribution

It presents a novel hybrid analog-digital memristor neural network that harnesses analog noise as a computational resource for solving NP-hard problems.

Findings

Successfully solves NP-hard max-cut problems in analog crossbar arrays.

Forecasts over four orders of magnitude higher solution throughput per power compared to digital and quantum approaches.

Demonstrates scalability and efficiency of memristor-based optimization at room temperature.

Abstract

We describe a hybrid analog-digital computing approach to solve important combinatorial optimization problems that leverages memristors (two-terminal nonvolatile memories). While previous memristor accelerators have had to minimize analog noise effects, we show that our optimization solver harnesses such noise as a computing resource. Here we describe a memristor-Hopfield Neural Network (mem-HNN) with massively parallel operations performed in a dense crossbar array. We provide experimental demonstrations solving NP-hard max-cut problems directly in analog crossbar arrays, and supplement this with experimentally-grounded simulations to explore scalability with problem size, providing the success probabilities, time and energy to solution, and interactions with intrinsic analog noise. Compared to fully digital approaches, and present-day quantum and optical accelerators, we forecast the mem-HNN to have over four orders of magnitude higher solution throughput per power consumption. This suggests substantially improved performance and scalability compared to current quantum annealing approaches, while operating at room temperature and taking advantage of existing CMOS technology augmented with emerging analog non-volatile memristors.