Litcius/Paper detail

Rotating neurons for all-analog implementation of cyclic reservoir computing

Xiangpeng Liang, Ya‐Nan Zhong, Jianshi Tang, Zhengwu Liu, Peng Yao, Keyang Sun, Qingtian Zhang, Bin Gao, Hadi Heidari, He Qian, Huaqiang Wu

2022Nature Communications122 citationsDOIOpen Access PDF

Abstract

Hardware implementation in resource-efficient reservoir computing is of great interest for neuromorphic engineering. Recently, various devices have been explored to implement hardware-based reservoirs. However, most studies were mainly focused on the reservoir layer, whereas an end-to-end reservoir architecture has yet to be developed. Here, we propose a versatile method for implementing cyclic reservoirs using rotating elements integrated with signal-driven dynamic neurons, whose equivalence to standard cyclic reservoir algorithm is mathematically proven. Simulations show that the rotating neuron reservoir achieves record-low errors in a nonlinear system approximation benchmark. Furthermore, a hardware prototype was developed for near-sensor computing, chaotic time-series prediction and handwriting classification. By integrating a memristor array as a fully-connected output layer, the all-analog reservoir computing system achieves 94.0% accuracy, while simulation shows >1000× lower system-level power than prior works. Therefore, our work demonstrates an elegant rotation-based architecture that explores hardware physics as computational resources for high-performance reservoir computing.

Topics & Concepts

Reservoir computingNeuromorphic engineeringComputer scienceBenchmark (surveying)Reconfigurable computingChaoticNonlinear systemComputer hardwareComputer engineeringComputational scienceParallel computingArtificial neural networkField-programmable gate arrayArtificial intelligenceRecurrent neural networkPhysicsGeodesyQuantum mechanicsGeographyNeural Networks and Reservoir ComputingAdvanced Memory and Neural ComputingNeural dynamics and brain function