模仿大脑发育机制，让AI持续学习多种认知功能。
Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanism
- 按从简单到复杂的顺序演化模块间长程连接
- 通过反馈抑制与剪枝减少冗余，降低能耗
- 无需重放缓存或冻结参数，适合长期学习
当前人工智能网络的认知能力随规模指数级增长，而人类大脑可在极低能耗下持续学习数百种认知功能。这得益于大脑跨区域的时间发展机制：连接从基础区域向高级区域逐步形成、重组与修剪，促进知识迁移并避免冗余。受此启发，我们提出脑启发式时序发展机制的多认知功能持续学习方法（TD-MCL），在感知-运动-交互（PMI）多任务场景中实现从简单到复杂的能力演进。该模型通过分阶段构建模块间长程连接以促进正向知识迁移，并采用反馈引导的局部连接抑制与剪枝，有效消除旧任务冗余，降低能耗同时保留已学知识。实验表明，该方法在不引入正则化、回放或冻结策略的前提下，实现了持续学习能力，网络规模更小，新任务准确率优于直接学习。结果表明，大脑发育机制为实现生物合理、低能耗的通用认知增强提供了重要参考。
原文摘要 · Abstract (English)
Cognitive functions in current artificial intelligence networks are tied to the exponential increase in network scale, whereas the human brain can continuously learn hundreds of cognitive functions with remarkably low energy consumption. This advantage is in part due to the brain cross-regional temporal development mechanisms, where the progressive formation, reorganization, and pruning of connections from basic to advanced regions, facilitate knowledge transfer and prevent network redundancy. Inspired by these, we propose the Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanism(TD-MCL), enabling cognitive enhancement from simple to complex in Perception-Motor-Interaction(PMI) multiple cognitive task scenarios. The TD-MCL model proposes the sequential evolution of long-range connections between different cognitive modules to promote positive knowledge transfer, while using feedback-guided local connection inhibition and pruning to effectively eliminate redundancies in previous tasks, reducing energy consumption while preserving acquired knowledge. Experiments show that the proposed method can achieve continual learning capabilities while reducing network scale, without introducing regularization, replay, or freezing strategies, and achieving superior accuracy on new tasks compared to direct learning. The proposed method shows that the brain's developmental mechanisms offer a valuable reference for exploring biologically plausible, low-energy enhancements of general cognitive abilities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。