基于WSBM的回声状态网络的动力学分析:使用InputDSA
Analyzing the Dynamics of WSBM-based Echo State Networks using InputDSA
AI总结:
该研究提出结合WSBM与ESNs的储备池计算框架,集成InputDSA分析结构先验对动力学的调节作用,证实动力学的安娜·卡列尼娜原理,发现结构多样性不一定预测行为多样性。
摘要:
弥合生物大脑与人工神经网络之间的结构差距,为改变计算动力学提供了途径。本文提出一种储备池计算框架,将加权随机块模型(WSBM)应用于回声状态网络(ESNs),用具有生物真实性的模块化结构替代随机网络。这种拓扑参数化构建了反映潜在功能子回路的储备池。此外,输入动力学相似性分析(InputDSA)的集成提供了一种机制,用于分离和比较结构先验如何调节内在循环动力学与外部输入。通过评估这些架构,我们确定在选定的网络子集上,结构多样性并不一定能预测行为多样性。此外,我们的解混分析证实了动力学的安娜·卡列尼娜原理,表明环境约束会促使成功智能体的动力学收敛,而失败的网络则退化为特异轨迹。
英文摘要:
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.
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。