The Ohio State University, Department of Physics, 191 West Woodruff Ave., Columbus, OH, 43210, USA.
ResCon Technologies, LLC, PO Box 21229, Columbus, OH, 43221, USA.
Nat Commun. 2021 Sep 21;12(1):5564. doi: 10.1038/s41467-021-25801-2.
Reservoir computing is a best-in-class machine learning algorithm for processing information generated by dynamical systems using observed time-series data. Importantly, it requires very small training data sets, uses linear optimization, and thus requires minimal computing resources. However, the algorithm uses randomly sampled matrices to define the underlying recurrent neural network and has a multitude of metaparameters that must be optimized. Recent results demonstrate the equivalence of reservoir computing to nonlinear vector autoregression, which requires no random matrices, fewer metaparameters, and provides interpretable results. Here, we demonstrate that nonlinear vector autoregression excels at reservoir computing benchmark tasks and requires even shorter training data sets and training time, heralding the next generation of reservoir computing.
储层计算是一种用于处理动态系统生成的信息的最优机器学习算法，使用观测到的时间序列数据。重要的是，它只需要非常小的训练数据集，使用线性优化，因此只需要最小的计算资源。然而，该算法使用随机抽样的矩阵来定义基础的递归神经网络，并且有许多必须优化的超参数。最近的结果表明，储层计算等同于不需要随机矩阵、更少超参数并提供可解释结果的非线性向量自回归。在这里，我们证明了非线性向量自回归在储层计算基准任务中表现出色，并且只需要更短的训练数据集和训练时间，预示着新一代储层计算的到来。
