Behavior-dLDS: A decomposed linear dynamical systems model for neural activity partially constrained by behavior

2026-03-05

AI Summary

Disentangling behavior-driven neural dynamics from internally generated computations in large-scale neural activity remains a central challenge in understanding the mechanisms of behavior generation. This work proposes behavioral factorized linear dynamical systems (b-dLDS), a novel framework that explicitly separates low-dimensional latent variables constrained by behavior from concurrent internal computational dynamics within a unified model. Unlike conventional approaches that impose behavioral supervision on all neural dynamics, b-dLDS overcomes this limitation by decoupling these components. The method outperforms existing behavior-supervised models on simulated data and successfully identifies dynamic neural subpopulations associated with postural homeostasis in recordings of tens of thousands of neurons from the zebrafish hindbrain. These results demonstrate that b-dLDS provides a powerful new tool for dissecting the neural basis of complex brain functions.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Behavior Learning & Control

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Brain-wide recordings of large-scale networks of neurons now provide an unprecedented view into how the brain drives behavior. However, brain activity contains both information directly related to behavior as well as the potential for many internal computations. Moreover, observable behavior is executed not only by the brain, but also by the spinal cord and peripheral nervous system. Behavior is a coarse-grained product of neural activity, and we thus take the view that it can be best represented by lower-dimensional latent neural dynamics. Capturing this indirect relationship while disambiguating behavior-generating networks from internal computations running in parallel requires new modeling approaches that can embody the parallel and distributed nature of large-scale neural populations. We thus present behavior-decomposed linear dynamical systems (b-dLDS) to disentangle simultaneously recorded subsystems and identify how the latent neural subsystems relate to behavior. We demonstrate the ability of b-dLDS to decouple behavioral vs. internal computations on controlled, simulated data, showing improvements over a state-of-the-art model that uses behavior to supervise all dynamics based on behavior. We then show that b-dLDS can further scale up to tens of thousands of neurons by applying our model to large-scale recording of a zebrafish hindbrain during the complex positional homeostasis behavior, wherein b-dLDS highlights behavior-related dynamic connectivity networks.

Problem

• neural dynamics
• behavioral decoding
• internal computation
• latent dynamics
• large-scale neural recordings

Innovation

• decomposed linear dynamical systems
• neural-behavioral disentanglement
• latent dynamics
• large-scale neural recordings
• behavior-constrained modeling