基于动态可用性的上下文选择性促进终身持续学习
Context selectivity with dynamic availability enables lifelong continual learning
浏览论文内容
中文总结 AI 辅助
本文提出基于上下文选择性和动态可用性的元可塑性规则，通过模拟验证该模型在图像识别和自然语言处理任务中优于现有持续学习算法。
中文摘要 AI 辅助
"你永远忘不了如何骑自行车"——但这是如何可能的？大脑能够学习复杂技能，停顿多年不练习，中间学习其他技能，仍能随时召回原始知识。这种能力的机制，称为终身学习（或持续学习，CL），尚不清楚。我们建议一种生物合理的元可塑性规则，基于经典持续学习工作，总结为两个原则：(i) 神经元具有上下文选择性，(ii) 一个局部可用性变量在神经元先前任务相关时部分冻结可塑性。在新的神经中心形式化中，我们建议神经元选择性和神经元级巩固是简单且可行的元可塑性假设，以在大脑中实现CL。在模拟中，该简单模型平衡了遗忘和巩固，导致在图像识别和自然语言处理CL基准上优于当前CL算法。
英文摘要
"You never forget how to ride a bike", -- but how is that possible? The brain is able to learn complex skills, stop the practice for years, learn other skills in between, and still retrieve the original knowledge when necessary. The mechanisms of this capability, referred to as lifelong learning (or continual learning, CL), are unknown. We suggest a bio-plausible meta-plasticity rule building on classical work in CL which we summarize in two principles: (i) neurons are context selective, and (ii) a local availability variable partially freezes the plasticity if the neuron was relevant for previous tasks. In a new neuro-centric formalization of these principles, we suggest that neuron selectivity and neuron-wide consolidation is a simple and viable meta-plasticity hypothesis to enable CL in the brain. In simulation, this simple model balances forgetting and consolidation leading to better transfer learning than contemporary CL algorithms on image recognition and natural language processing CL benchmarks.
发表机构
- Department of Life Sciences, Department of Computer Sciences（生命科学系、计算机科学系）
机构由 AI 辅助整理，请以论文原文为准。
