HiCL：基于海马体的持续学习
HiCL: Hippocampal-Inspired Continual Learning
AI总结：
HiCL提出了一种基于海马体的持续学习架构，通过双记忆机制和稀疏路由策略减少任务干扰，实现高效多任务学习。
摘要：
我们提出HiCL，一种新的基于海马体的双记忆持续学习架构，旨在通过使用受海马体回路启发的元素来缓解灾难性遗忘。我们的系统通过类似网格细胞的层编码输入，随后使用受海马体 dentate gyrus 激活的模块进行稀疏模式分离，采用top-k稀疏性。事件记忆轨迹通过类似于CA3的自关联记忆维护。任务特定处理通过DG门控的混合专家机制动态管理，其中输入根据其归一化稀疏DG表示与通过在线指数移动平均计算的学得任务特定DG原型之间的余弦相似性路由到专家。这种生物启发但数学上严谨的门控策略使能够实现可微、可扩展的任务路由，而无需依赖单独的门控网络，并增强了模型在学习多个连续任务时的适应性和效率。皮层输出通过弹性权重巩固进行巩固，权重由跨任务相似性加权。关键的是，我们纳入了优先级回放存储模式以强化重要的过去经验。在标准持续学习基准上的评估表明，我们的架构在减少任务干扰方面是有效的，以较低的计算成本实现了持续学习任务的近最先进的结果。我们的代码可用在此处https://github.com/kushalk173-sc/HiCL。
英文摘要：
We propose HiCL, a novel hippocampal-inspired dual-memory continual learning architecture designed to mitigate catastrophic forgetting by using elements inspired by the hippocampal circuitry. Our system encodes inputs through a grid-cell-like layer, followed by sparse pattern separation using a dentate gyrus-inspired module with top-k sparsity. Episodic memory traces are maintained in a CA3-like autoassociative memory. Task-specific processing is dynamically managed via a DG-gated mixture-of-experts mechanism, wherein inputs are routed to experts based on cosine similarity between their normalized sparse DG representations and learned task-specific DG prototypes computed through online exponential moving averages. This biologically grounded yet mathematically principled gating strategy enables differentiable, scalable task-routing without relying on a separate gating network, and enhances the model's adaptability and efficiency in learning multiple sequential tasks. Cortical outputs are consolidated using Elastic Weight Consolidation weighted by inter-task similarity. Crucially, we incorporate prioritized replay of stored patterns to reinforce essential past experiences. Evaluations on standard continual learning benchmarks demonstrate the effectiveness of our architecture in reducing task interference, achieving near state-of-the-art results in continual learning tasks at lower computational costs. Our code is available here https://github.com/kushalk173-sc/HiCL.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
