Scholarlink

<p>This study investigates attractor reconstruction via reservoir computing, focusing on how the reservoir’s structural constraints influence the learned dynamics. As a case study, we analyze the state space of a standard echo state network (ESN) trained to reconstruct the Lorenz system. As model parameters vary, the reconstructed attractor undergoes crises and decomposes into two spiral structures divided by a saddle point—an artifact absent in the original Lorenz system. This phenomenon suggests that the ESN forms a pseudo-Lorenz double-spiral attractor, which can be interpreted as a manifestation of the reservoir’s intrinsic constraints, such as symmetry and nonlinearity. The interaction between such constraints and the teacher data is an inherent aspect of the attractor reconstruction task by reservoir computing.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Pseudo-Lorenz attractors in echo state networks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月10日

查看全文
  • Tempei Kabayama,
  • Motomasa Komuro,
  • Kazuyuki Aihara,
  • Kohei Nakajima

摘要

This study investigates attractor reconstruction via reservoir computing, focusing on how the reservoir’s structural constraints influence the learned dynamics. As a case study, we analyze the state space of a standard echo state network (ESN) trained to reconstruct the Lorenz system. As model parameters vary, the reconstructed attractor undergoes crises and decomposes into two spiral structures divided by a saddle point—an artifact absent in the original Lorenz system. This phenomenon suggests that the ESN forms a pseudo-Lorenz double-spiral attractor, which can be interpreted as a manifestation of the reservoir’s intrinsic constraints, such as symmetry and nonlinearity. The interaction between such constraints and the teacher data is an inherent aspect of the attractor reconstruction task by reservoir computing.