Rotating neurons for all-analog implementation of cyclic reservoir computing

• Published in: Nature communications Vol. 13; no. 1; pp. 1549 - 11
• Main Authors: Liang, Xiangpeng, Zhong, Yanan, Tang, Jianshi, Liu, Zhengwu, Yao, Peng, Sun, Keyang, Zhang, Qingtian, Gao, Bin, Heidari, Hadi, Qian, He, Wu, Huaqiang
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 23.03.2022; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166; 639/166/987; 639/705/1042; Algorithms; Circuits; CMOS; Computer Simulation; Computers; Handwriting; Hardware; Humanities and Social Sciences; Memristors; multidisciplinary; Neural Networks, Computer; Neurons; Neurons - physiology; Nonlinear systems; Power; Rotation; Science; Science (multidisciplinary)
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-022-29260-1

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. Reservoir computing has demonstrated high-level performance, however efficient hardware implementations demand an architecture with minimum system complexity. The authors propose a rotating neuron-based architecture for physically implementing all-analog resource efficient reservoir computing system.