受大脑双系统启发，用符号推理防止神经网络遗忘旧知识
Hybrid Learners Do Not Forget: A Brain-Inspired Neuro-Symbolic Approach to Continual Learning
- 用神经网络快速学新任务，符号系统长期保存旧知识
- 在两个新基准上表现优于纯神经网络方法，遗忘率显著降低
- 适合需要长期学习且不能丢掉旧知识的智能系统场景
持续学习对实现可自主学习与进化的AI代理至关重要。其主要挑战在于学习新任务时不丢失已有知识。现有方法多依赖神经网络机制缓解遗忘。受人类大脑系统1（直觉）与系统2（推理）的启发，我们提出神经符号脑启发持续学习框架（NeSyBiCL），包含两个子系统：一个神经网络模型快速适应最新任务，一个符号推理器保留过往任务的知识。我们设计了两者的融合机制，促进符号知识向神经网络迁移。此外，我们构建了两个组合式持续学习基准，并证明NeSyBiCL在性能上优于仅依赖神经架构的方法，有效缓解遗忘。
原文摘要 · Abstract (English)
Continual learning is crucial for creating AI agents that can learn and improve themselves autonomously. A primary challenge in continual learning is to learn new tasks without losing previously learned knowledge. Current continual learning methods primarily focus on enabling a neural network with mechanisms that mitigate forgetting effects. Inspired by the two distinct systems in the human brain, System 1 and System 2, we propose a Neuro-Symbolic Brain-Inspired Continual Learning (NeSyBiCL) framework that incorporates two subsystems to solve continual learning: A neural network model responsible for quickly adapting to the most recent task, together with a symbolic reasoner responsible for retaining previously acquired knowledge from previous tasks. Moreover, we design an integration mechanism between these components to facilitate knowledge transfer from the symbolic reasoner to the neural network. We also introduce two compositional continual learning benchmarks and demonstrate that NeSyBiCL is effective and leads to superior performance compared to continual learning methods that merely rely on neural architectures to address forgetting.
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。