Joint sparse coding and temporal dynamics support context reconfiguration
2026-05-11 • Machine Learning
Machine LearningNeural and Evolutionary Computing
AI summaryⓘ
The authors studied how the brain can switch between different situations without forgetting what it learned before. They found that the brain uses a combination of sparse coding—where only some neurons are active in each context—and timing patterns in neural activity to keep memories separate and stable. They showed these ideas also work in computer models, which could help prevent forgetting in AI systems that learn over time. This suggests that sparse coding and timing are key ways the brain adapts flexibly but keeps old knowledge intact.
adaptive behaviorsparse codingmedial prefrontal cortextemporal dynamicscontext representationlifelong learningcatastrophic forgettingspiking neural networksneural representationscross-context interference
Authors
Qianqian Shi, Yue Che, Faqiang Liu, Hongyi Li, Mingkun Xu, Sandra Reinert, Pieter M. Goltstein, Rong Zhao, Luping Shi
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.