论文标题
Euler州网络：非截止性储层计算
Euler State Networks: Non-dissipative Reservoir Computing
论文作者
论文摘要
受普通微分方程的数值解的启发，在本文中，我们提出了一种新型的储层计算（RC）模型，称为Euler State Network（EUSN）。提出的方法利用前向Euler离散化和反对称复发矩阵来设计储层动力学，这些动力学既稳定又不划分。 我们的数学分析表明，所得模型偏向统一的有效光谱半径和零局部Lyapunov指数，本质上在稳定性的边缘附近运行。长期记忆任务的实验表明，在需要有效传播输入信息在多个时步上的问题中，提出的方法比标准RC模型的明显优势。此外，计时序列分类基准的结果表明，EUSN能够匹配（甚至超过）可训练的复发性神经网络的准确性，同时保留了RC家族的培训效率，最高$ \ $ \ $ \ $ \ $ 490倍，计算时间和$ \ $ \ $ \ $ \ \ \ \ \ \ \左右的能源消耗$ 1750升。
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.
