A Foundational Brain Dynamics Model via Stochastic Optimal Control

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Park, Joonhyeong, Park, Byoungwoo, Bang, Chang-Bae, Choi, Jungwon, Chung, Hyungjin, Kim, Byung-Hoon, Lee, Juho
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913683396886528
author Park, Joonhyeong
Park, Byoungwoo
Bang, Chang-Bae
Choi, Jungwon
Chung, Hyungjin
Kim, Byung-Hoon
Lee, Juho
author_facet Park, Joonhyeong
Park, Byoungwoo
Bang, Chang-Bae
Choi, Jungwon
Chung, Hyungjin
Kim, Byung-Hoon
Lee, Juho
contents We introduce a foundational model for brain dynamics that utilizes stochastic optimal control (SOC) and amortized inference. Our method features a continuous-discrete state space model (SSM) that can robustly handle the intricate and noisy nature of fMRI signals. To address computational limitations, we implement an approximation strategy grounded in the SOC framework. Additionally, we present a simulation-free latent dynamics approach that employs locally linear approximations, facilitating efficient and scalable inference. For effective representation learning, we derive an Evidence Lower Bound (ELBO) from the SOC formulation, which integrates smoothly with recent advancements in self-supervised learning (SSL), thereby promoting robust and transferable representations. Pre-trained on extensive datasets such as the UKB, our model attains state-of-the-art results across a variety of downstream tasks, including demographic prediction, trait analysis, disease diagnosis, and prognosis. Moreover, evaluating on external datasets such as HCP-A, ABIDE, and ADHD200 further validates its superior abilities and resilience across different demographic and clinical distributions. Our foundational model provides a scalable and efficient approach for deciphering brain dynamics, opening up numerous applications in neuroscience.
format Preprint
id arxiv_https___arxiv_org_abs_2502_04892
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Foundational Brain Dynamics Model via Stochastic Optimal Control
Park, Joonhyeong
Park, Byoungwoo
Bang, Chang-Bae
Choi, Jungwon
Chung, Hyungjin
Kim, Byung-Hoon
Lee, Juho
Machine Learning
Neurons and Cognition
We introduce a foundational model for brain dynamics that utilizes stochastic optimal control (SOC) and amortized inference. Our method features a continuous-discrete state space model (SSM) that can robustly handle the intricate and noisy nature of fMRI signals. To address computational limitations, we implement an approximation strategy grounded in the SOC framework. Additionally, we present a simulation-free latent dynamics approach that employs locally linear approximations, facilitating efficient and scalable inference. For effective representation learning, we derive an Evidence Lower Bound (ELBO) from the SOC formulation, which integrates smoothly with recent advancements in self-supervised learning (SSL), thereby promoting robust and transferable representations. Pre-trained on extensive datasets such as the UKB, our model attains state-of-the-art results across a variety of downstream tasks, including demographic prediction, trait analysis, disease diagnosis, and prognosis. Moreover, evaluating on external datasets such as HCP-A, ABIDE, and ADHD200 further validates its superior abilities and resilience across different demographic and clinical distributions. Our foundational model provides a scalable and efficient approach for deciphering brain dynamics, opening up numerous applications in neuroscience.
title A Foundational Brain Dynamics Model via Stochastic Optimal Control
topic Machine Learning
Neurons and Cognition
url https://arxiv.org/abs/2502.04892