Sufficient conditions for offline reactivation in recurrent neural networks

TL;DR

This paper develops a mathematical framework to identify conditions under which neural networks can autonomously reactivate states associated with online behavior during offline periods, such as sleep.

Contribution

It introduces a theoretical model showing how task-optimized noisy recurrent networks naturally develop reactivation dynamics, supported by numerical experiments.

Findings

Neural networks can spontaneously revisit online states during offline periods.

Denoising dynamics emerge in networks optimized for environmental tracking.

Theoretical results are validated with neuroscience-inspired tasks.

Abstract

During periods of quiescence, such as sleep, neural activity in many brain circuits resembles that observed during periods of task engagement. However, the precise conditions under which task-optimized networks can autonomously reactivate the same network states responsible for online behavior is poorly understood. In this study, we develop a mathematical framework that outlines sufficient conditions for the emergence of neural reactivation in circuits that encode features of smoothly varying stimuli. We demonstrate mathematically that noisy recurrent networks optimized to track environmental state variables using change-based sensory information naturally develop denoising dynamics, which, in the absence of input, cause the network to revisit state configurations observed during periods of online activity. We validate our findings using numerical experiments on two canonical neuroscience tasks: spatial position estimation based on self-motion cues, and head direction estimation based on angular velocity cues. Overall, our work provides theoretical support for modeling offline reactivation as an emergent consequence of task optimization in noisy neural circuits.