arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.20147nlin.CDcond-mat.dis-nncond-mat.stat-mechnlin.AO
收藏

回声状态网络(ESN)的在线训练用于预测混沌动力系统

Online training of Echo State Networks to predict chaotic dynamical systems

Institute of Nanoscience and Nanotechnology, National Center for Scientific Research “Demokritos”(纳米科学与纳米技术研究所,德谟克利特国家科学研究中心);Institute of Electronic Structure and Laser, Foundation for Research and Technology-Hellas(电子结构与激光研究所,希腊研究与技术基金会)

Astero Provata, Markos Syroukis, Johanne Hizanidis

AI总结:

本研究探讨储备池拓扑对ESN在线训练预测混沌动力系统性能的影响,发现稀疏Erdos-Renyi储备池及小连接密度的Watts & Strogatz储备池表现最优,为动态系统实时预测提供高效框架。

摘要:

回声状态网络(Echo State Networks, ESNs)从人工智能的概念视角来看具有根本重要性,因为它们为理解动力系统中的时间信息处理、记忆和学习提供了简单且易于处理的框架。ESNs由一个相互连接的储备池构成,其连接矩阵随时间保持恒定,仅在训练期间更新输出权重。特别是,采用在线训练的ESNs能够在接收数据时对输出权重进行增量调整,这使得它们特别适用于新输入数据随时间不断产生的应用场景(非平稳环境)。研究这类学习结构的一个关键目标是确定储备池的哪些统计特性能提升计算效率并最大化预测性能。为此,我们研究了储备池拓扑对学习性能的影响,考虑了由Erdos-Renyi随机网络和Watts & Strogatz小世界网络生成的权重矩阵。测试数据采用混沌状态下的Lorenz模型和Rossler模型,以及极限环状态下的FitzHugh-Nagumo模型。对于随机Erdos-Renyi储备池,我们的模拟显示,稀疏储备池能获得最佳性能,尤其是当连接密度接近且略高于平均场键渗流临界点时。Watts & Strogatz储备池在较小的连接密度下也表现出最佳性能,当考虑到Watts & Strogatz储备池特定的非局部环结构时,该性能与平均场键渗流相符。这些关于储备池架构和超参数对提升ESN预测准确性影响的研究,为动态演化系统中的实时预测提供了高效框架。

英文摘要:

Echo State Networks (ESNs) are fundamentally important from the conceptual perspective of AI, because they provide simple and tractable frameworks for understanding temporal information processing, memory, and learning in dynamical systems. They are composed by an interconnected reservoir whose connectivity matrix remains constant over time and only the output weights are updated during the training period. In particular, ESNs employing online training allow the incremental adaptation of the output weights as data is received, making them particularly suitable for applications in which new input data becomes available over time (non-stationary environments). A key objective in the study of such learning structures is to determine which statistical properties of the reservoir enhance computational efficiency and maximize prediction performance. To this end, we investigate the effects of reservoir topology on learning performance, considering weight matrices generated from Erdos-Renyi random networks and Watts & Strogatz small-world networks. As test data we use the Lorenz and Rossler models in the chaotic regime and the FitzHugh-Nagumo model in the limit cycle regime. In the case of random Erdos-Renyi reservoirs, our simulations show that best performances are obtained for sparse reservoirs and especially when the link-density is near and immediately above the critical point of mean-field bond percolation. Watts & Strogatz reservoirs are shown to demonstrate best performance also for small values of link-density, compatible with the mean-field bond percolation when taking into account the specific nonlocal ring structure of the Watts & Strogatz reservoirs. These studies on the influence of the reservoir architecture and hyperparameters on enhancing the accuracy of ESN predictions provide an efficient framework for real-time forecasting in dynamically evolving systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑