arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.18566cs.LGcs.SYeess.SYq-bio.NC
收藏

通过微分同胚向量场对齐比较动力学模型

Comparing Dynamical Models Through Diffeomorphic Vector Field Alignment

Washington University in St. Louis(华盛顿大学圣路易斯分校)

Ruiqi Chen, Giacomo Vedovati, Todd Braver, ShiNung Ching

AI总结:

提出DFORM框架,通过非线性坐标变换对齐两个动力系统的轨迹,评估拓扑等价性并定位高维模型中的低维动力学模式。

摘要:

诸如递归神经网络(RNN)等动力系统模型在理论神经科学中越来越受欢迎,用于假设生成和数据分析。评估这些模型中的动力学是理解其学习到的生成机制的关键。然而,这种评估受到两个主要挑战的阻碍:首先,由于没有强制要求坐标系统等价,跨模型比较学习到的动力学很困难。其次,在高维非线性模型(如RNN)中,识别机制上重要的低维模式(例如极限集)是难以处理的。在这里,我们提出了一个全面的框架来解决这两个问题,称为学习模型的微分同胚向量场对齐(DFORM)。DFORM学习两个动力系统状态空间之间的非线性坐标变换,以最大程度地一对一地对齐它们的轨迹。通过这样做,DFORM能够评估两个模型是否表现出拓扑等价性,即尽管坐标系统不同但机制相似。该方法的一个副产品是一种在高维系统中嵌入的低维流形上定位动力学模式的方法。我们使用典型的拓扑等价系统、RNN和通过非线性流相关的系统验证了DFORM识别线性和非线性坐标变换的能力。DFORM还被证明可以提供拓扑不同系统之间的相似性量化。然后,我们证明了DFORM可以在高维模型中定位重要的动力学模式,包括不变流形和鞍极限集。最后,使用一组在人类功能性磁共振成像(fMRI)记录上训练的RNN模型,我们展示了DFORM可以从高维数据驱动模型中识别极限环,这与先前的数值分析结果一致。

英文摘要:

Dynamical systems models such as recurrent neural networks (RNNs) are increasingly popular in theoretical neuroscience for hypothesis-generation and data analysis. Evaluating the dynamics in such models is key to understanding their learned generative mechanisms. However, such evaluation is impeded by two major challenges: First, comparison of learned dynamics across models is difficult because there is no enforced equivalence of their coordinate systems. Second, identification of mechanistically important low-dimensional motifs (e.g., limit sets) is intractable in high-dimensional nonlinear models such as RNNs. Here, we propose a comprehensive framework to address these two issues, termed Diffeomorphic vector field alignment FOR learned Models (DFORM). DFORM learns a nonlinear coordinate transformation between the state spaces of two dynamical systems, which aligns their trajectories in a maximally one-to-one manner. In so doing, DFORM enables an assessment of whether two models exhibit topological equivalence, i.e., similar mechanisms despite differences in coordinate systems. A byproduct of this method is a means to locate dynamical motifs on low-dimensional manifolds embedded within higher-dimensional systems. We verified DFORM's ability to identify linear and nonlinear coordinate transformations using canonical topologically equivalent systems, RNNs, and systems related by nonlinear flows. DFORM was also shown to provide a quantification of similarity between topologically distinct systems. We then demonstrated that DFORM can locate important dynamical motifs including invariant manifolds and saddle limit sets within high-dimensional models. Finally, using a set of RNN models trained on human functional MRI (fMRI) recordings, we illustrated that DFORM can identify limit cycles from high-dimensional data-driven models, which agreed well with prior numerical analysis.

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。

↑