Sparse reservoir computing with vertically coupled vortex spin-torque oscillators for time series prediction.
Haobo Shen, Lie Xu, Menghao Jin, Hai Li, Changqiu Yu, Bo Liu, Tiejun Zhou
Author Information
Haobo Shen: School of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, People's Republic of China. ORCID
Lie Xu: School of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, People's Republic of China. ORCID
Menghao Jin: School of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, People's Republic of China.
Hai Li: School of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, People's Republic of China.
Changqiu Yu: School of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, People's Republic of China.
Bo Liu: Key Laboratory of Spintronics Materials, Devices and Systems of Zhejiang Province, Hangzhou, Zhejiang 311305, People's Republic of China.
Tiejun Zhou: School of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, People's Republic of China. ORCID
Spin torque nano-oscillators possessing fast nonlinear dynamics and short-term memory functions are potentially able to achieve energy-efficient neuromorphic computing. In this study, we introduce an activation-state controllable spin neuron unit composed of vertically coupled vortex spin torque oscillators and a-source circuit is proposed and used to build an energy-efficient sparse reservoir computing (RC) system to solve nonlinear dynamic system prediction task. Based on micromagnetic and electronic circuit simulation, the Mackey-Glass chaotic time series and the real motor vibration signal series can be predicted by the RC system with merely 20 and 100 spin neuron units, respectively. Further study shows that the proposed sparse reservoir system could reduce energy consumption without significantly compromising performance, and a minimal response from inactivated neurons is crucial for maintaining the system's performance. The accuracy and signal processing speed show the potential of the proposed sparse RC system for high-performance and low-energy neuromorphic computing.
