Boosting learning ability of overdamped bistable stochastic resonance system based physical reservoir computing model by time-delayed feedback. (August 2022)

• Record Type: Journal Article
• Authors: Shi, Zhuozheng; Liao, Zhiqiang; Tabata, Hitoshi
• Is Part Of: Chaos, solitons and fractals. Volume 161(2022)
• Publication Date: 2022-08
• Subjects: Reservoir computing -- Short-term memory ability -- Overdamped bistable system -- Stochastic resonance -- Time-delayed feedback; Chaotic behavior in systems -- Periodicals; Solitons -- Periodicals; Fractals -- Periodicals; Chaotic behavior in systems; Fractals; Solitons; Periodicals; 003.7
• DOI: 10.1016/j.chaos.2022.112314
• Languages: English
• ISSNs: 0960-0779

Abstract

Abstract: Physical reservoir computing (RC), which can be implemented by various physical systems, is a low-cost neuromorphic framework with a fast learning capability. In the previous studies, an overdamped bistable system-based RC (OBRC) inspired by the FitzHugh-Nagumo neuron model has been proposed to construct an outstanding physical RC system. Benefitting from the stochastic resonance effect, the OBRC requires less power and has stronger noise robustness than many conventional physical RC systems. However, compared with conventional physical RC systems, its learning ability is not superior. To boost the performance of the OBRC, we propose an OBRC with time-delayed feedback (TOBRC). In this work, the TOBRC is implemented in a physical setting with time-multiplexing nodes design and simulated on a conventional computer. Moreover, we adopt a powerful optimization algorithm to automatically determine the optimal hyperparameters for both the OBRC and TOBRC; thus, a more precise quantitative discussion on the upper limit of the system can be made. To compare the TOBRC and OBRC, we conducted short-term memory and parity check tasks to assess the short-term memory ability and nonlinearity, which are the two core abilities of physical RC for learning. The results prove that the short-term memory ability and nonlinearity of the proposed TOBRC are 6.46 and 2.15 times higher than those of the OBRC, respectively. Moreover, the TOBRC outperforms the OBRC under different noise conditions. On the MNIST handwritten digit recognition benchmark, the TOBRC exhibited a lower error rate than the OBRC; it was comparable with that of advanced physical RC systems. Our study confirms that the TOBRC can exhibit excellent learning ability in practical problems. Highlights: Traditional overdamped bistable physical reservoir computing model (OBRC) is improved by adding time-delayed feedback. Hyperparameters are optimized for discussing the upper limit of system performance more accurately. The short-term memory ability and nonlinearity of the proposed model are 6.46 and 2.15 times higher than those of the OBRC, respectively. In MNIST handwritten digit recognition task, the error rate of the proposed model is only 59 % of that of the OBRC.