arXiv：cs.AI· Huy Mai, Robert Clarke·· 16 小时前
基于 WSBM 的 Echo State Networks 动力学分析：InputDSA 方法
Analyzing the Dynamics of WSBM-based Echo State Networks using InputDSA
AI 导读
该论文提出一种 Reservoir Computing 框架，用 Weighted Stochastic Block Model（WSBM）替代随机网络，为 Echo State Networks（ESNs）构建具有生物模块化特征的储备池。
正文
Abstract:Bridging the structural gap between biological brains and artificial neural networks presents a pathway to altered computational dynamics. This paper introduces a Reservoir Computing framework that replaces random networks with biologically realistic modularity by applying the Weighted Stochastic Block Model (WSBM) to Echo State Networks (ESNs). This topological parameterization constructs reservoirs reflecting latent functional sub-circuits. Furthermore, the integration of Input Dynamical Similarity Analysis (InputDSA) provides a mechanism to isolate and compare how structural priors modulate intrinsic recurrent dynamics versus external inputs. By evaluating these architectures, we establish that structural diversity does not necessarily predicts behavioral diversity across the selected network subset. Furthermore, our demixed analysis confirms Anna Karenina principle of dynamics, demonstrating that environmental constraints enforce dynamical convergence in successful agents, while failing networks degenerate into idiosyncratic trajectories.
| Comments: | 9 pages excluding refs and appendices, 9 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.15380 [cs.AI] |
| (or arXiv:2610.15380v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15380 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Huy Mai [view email]
[v1]
Sun, 11 Oct 2026 06:08:02 UTC (6,715 KB)
来源：arXiv：cs.AI · arxiv.org