Joint sparse coding and temporal dynamics support context reconfiguration

2026-05-11

AI Summary

This work addresses the core challenge in lifelong learning of avoiding catastrophic forgetting while switching contexts in dynamic environments. The authors propose a novel mechanism that integrates sparse coding with the temporal dynamics of neural activity to enable flexible reconfiguration and stable maintenance of context representations, demonstrated both in the mouse medial prefrontal cortex and spiking neural networks. By jointly modeling collaborative sparsity and temporal dynamics as the foundation of contextual learning, the approach significantly enhances knowledge retention without relying on additional heuristic strategies. Moreover, it exhibits superior energy efficiency, offering a biologically plausible and computationally effective solution for continual learning under changing contextual demands.

Abstract

Adaptive behavior requires the brain to transition between distinct contexts while maintaining representations of prior experience. The ability to reconfigure neural representations without erasing previously acquired knowledge is central to learning in dynamic environments, yet the neural mechanisms that support this balance remain unclear. Understanding these mechanisms is also critical for addressing catastrophic forgetting in artificial systems designed for lifelong learning. Here, we identify joint sparse coding and temporal dynamics in both the mouse medial prefrontal cortex (mPFC) and computational networks as mechanisms that help preserve prior representations during context transitions. Specifically, sparsity in context-dependent representations reduces cross-context interference, whereas temporal dynamics within the network activity further enhance context separability across time. Strikingly, networks endowed with both properties, such as spiking neural networks, exhibit improved retention during lifelong learning without auxiliary heuristics. These findings establish joint sparse coding and temporal dynamics as a core mechanism supporting flexible context reconfiguration in lifelong learning and, through their activity constraining nature, as an energy-efficient architectural principle for stable adaptation. Together, they provide a mechanistic framework for understanding how the brain preserves prior knowledge while flexibly adapting to new contexts.

Problem

• context reconfiguration
• catastrophic forgetting
• lifelong learning
• neural representations
• temporal dynamics

Innovation

• joint sparse coding
• temporal dynamics
• context reconfiguration
• lifelong learning
• catastrophic forgetting