Inspired by the numerical solution of ordinary differential equations, in this paper we propose a novel Reservoir Computing (RC) model, called the Euler State Network (EuSN). The presented approach makes use of forward Euler discretization and antisymmetric recurrent matrices to design reservoir dynamics that are both stable and non-dissipative by construction. Our mathematical analysis shows that the resulting model is biased towards a unitary effective spectral radius and zero local Lyapunov exponents, intrinsically operating near to the edge of stability. Experiments on long-term memory tasks show the clear superiority of the proposed approach over standard RC models in problems requiring effective propagation of input information over multiple time-steps. Furthermore, results on time-series classification benchmarks indicate that EuSN is able to match (or even exceed) the accuracy of trainable Recurrent Neural Networks, while retaining the training efficiency of the RC family, resulting in up to $\approx$ 490-fold savings in computation time and $\approx$ 1750-fold savings in energy consumption.
翻译:受常微分方程的数值解启发,本文提出了一种新颖的储备计算(RC)模型,称为 Euler State Network (EuSN)。所提出的方法利用正向欧拉离散化和反对称循环矩阵设计了一种稳定且非耗散性的储备动态。我们的数学分析表明,所得到的模型有利于单元有效谱半径和局部李雅普诺夫指数为零,本质上在稳定性边缘附近运行。长期记忆任务的实验结果显示,所提出的方法在需要有效传播多个时间步的输入信息的问题上,比标准 RC 模型表现更好。此外,基于时间序列分类基准测试的结果表明,EuSN 能够匹配(甚至超过)可训练循环神经网络的准确性,同时保留了 RC 家族的训练效率,导致计算时间节约高达约 490 倍,能量消耗节约高达约 1,750 倍。