Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Brenner, Manuel, Weber, Elias, Koppe, Georgia, Durstewitz, Daniel
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909495228104704
author Brenner, Manuel
Weber, Elias
Koppe, Georgia
Durstewitz, Daniel
author_facet Brenner, Manuel
Weber, Elias
Koppe, Georgia
Durstewitz, Daniel
contents In science, we are often interested in obtaining a generative model of the underlying system dynamics from observed time series. While powerful methods for dynamical systems reconstruction (DSR) exist when data come from a single domain, how to best integrate data from multiple dynamical regimes and leverage it for generalization is still an open question. This becomes particularly important when individual time series are short, and group-level information may help to fill in for gaps in single-domain data. Here we introduce a hierarchical framework that enables to harvest group-level (multi-domain) information while retaining all single-domain characteristics, and showcase it on popular DSR benchmarks, as well as on neuroscience and medical data. In addition to faithful reconstruction of all individual dynamical regimes, our unsupervised methodology discovers common low-dimensional feature spaces in which datasets with similar dynamics cluster. The features spanning these spaces were further dynamically highly interpretable, surprisingly in often linear relation to control parameters that govern the dynamics of the underlying system. Finally, we illustrate transfer learning and generalization to new parameter regimes, paving the way toward DSR foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04814
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data
Brenner, Manuel
Weber, Elias
Koppe, Georgia
Durstewitz, Daniel
Machine Learning
Artificial Intelligence
Dynamical Systems
Chaotic Dynamics
Data Analysis, Statistics and Probability
In science, we are often interested in obtaining a generative model of the underlying system dynamics from observed time series. While powerful methods for dynamical systems reconstruction (DSR) exist when data come from a single domain, how to best integrate data from multiple dynamical regimes and leverage it for generalization is still an open question. This becomes particularly important when individual time series are short, and group-level information may help to fill in for gaps in single-domain data. Here we introduce a hierarchical framework that enables to harvest group-level (multi-domain) information while retaining all single-domain characteristics, and showcase it on popular DSR benchmarks, as well as on neuroscience and medical data. In addition to faithful reconstruction of all individual dynamical regimes, our unsupervised methodology discovers common low-dimensional feature spaces in which datasets with similar dynamics cluster. The features spanning these spaces were further dynamically highly interpretable, surprisingly in often linear relation to control parameters that govern the dynamics of the underlying system. Finally, we illustrate transfer learning and generalization to new parameter regimes, paving the way toward DSR foundation models.
title Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Data
topic Machine Learning
Artificial Intelligence
Dynamical Systems
Chaotic Dynamics
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2410.04814