Boosting learning ability of overdamped bistable stochastic resonance system based physical reservoir computing model by time-delayed feedback
Boosting learning ability of overdamped bistable stochastic resonance system based physical reservoir computing model by time-delayed feedback
复制标题
DOI：
10.1016/j.chaos.2022.112314
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Zhuozheng Shi;Zhiqiang Liao;H. Tabata
中科院分区：
文献类型：
--
作者：
Zhuozheng Shi;Zhiqiang Liao;H. Tabata
物理储层计算（RC）可以由各种物理系统实现，是一种具有快速学习能力的低成本神经形态框架。在之前的研究中，受 FitzHugh-Nagumo 神经元模型启发，提出了基于过阻尼双稳态系统的 RC（OBRC），以构建出色的物理 RC 系统。受益于随机谐振效应，OBRC 比许多传统的物理 RC 系统需要更少的功率，并且具有更强的噪声鲁棒性。然而，与传统的物理RC系统相比，它的学习能力并不优越。为了提高 OBRC 的性能，我们提出了带有延时反馈的 OBRC（TOBRC）。在这项工作中，TOBRC 在物理环境中实现，采用时分复用节点设计并在传统计算机上进行模拟。此外，我们采用强大的优化算法来自动确定OBRC和TOBRC的最佳超参数；从而可以对系统的上限进行更精确的定量讨论。为了比较 TOBRC 和 OBRC，我们进行了短期记忆和奇偶校验任务，以评估短期记忆能力和非线性，这是物理 RC 学习的两个核心能力。结果证明，所提出的 TOBRC 的短期记忆能力和非线性度分别是 OBRC 的 6.46 倍和 2.15 倍。此外，在不同噪声条件下，TOBRC 的性能优于 OBRC。在 MNIST 手写数字识别基准上，TOBRC 的错误率低于 OBRC；它可与先进的物理 RC 系统相媲美。我们的研究证实，TOBRC 可以在实际问题中表现出出色的学习能力。
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.