Engram Neuron Inspired Adaptive Memorization for Lifelong Learning

arXiv:2610.14940v1 Announce Type: new Abstract: Lifelong learning enables artificial systems to adapt to changing environments. To achieve this, an effective artificial learner should dynamically reorganize past and new experiences, maintaining stability while enabling flexible knowledge integration. However, existing efforts primarily mitigate catastrophic forgetting, lacking the ability to adaptively update memory akin to biological systems. Here, by integrating the full memory life cycle of engram neurons into artificial learners, we propose a framework that constructs a structured memory from gradient representations, which regulates parameter updates and guides memory management. Through comprehensive evaluations on four benchmarks, our approach shows promising lifelong learning capability, maintaining stability over long task sequences and supporting flexible adaptation. Beyond the performance gains, our approach offers a computational perspective on robust and flexible lifelong learning, echoing mechanisms observed in biological memory systems.

Related

• Parameter Efficient Continual Learning for Sparse Event-Based Transformers
• Towards Lifelong Aerial Autonomy: Geometric Memory Management for Continual Visual Place Recognition in Dynamic Environments
• HuMemSLAM: Efficient Human-Inspired Semantic Place Recognition for Robust Visual SLAM
• MECAIL: Communication-Aware Incremental Learning for Object Detection with 14.6 KB Spatiotemporal Experts

Source: arXiv cs.CV | 2026-10-14