"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.

翻译：“你永远不会忘记如何骑自行车”——但这怎么可能呢？大脑能够学习复杂技能，中断练习多年，期间学习其他技能，并在需要时仍然能检索原始知识。这种被称为终身学习（或持续学习，CL）的能力机制尚不明确。我们基于持续学习领域的经典工作，提出一种生物可解释的元可塑性规则，并将其总结为两个原则：（i）神经元具有上下文选择性，以及（ii）若神经元与先前任务相关，则局部可用性变量会部分冻结其可塑性。在对这些原则进行以神经元为中心的崭新形式化描述中，我们认为神经元选择性和全神经元巩固是使大脑实现持续学习的简单且可行的元可塑性假说。在仿真中，这一简单模型平衡了遗忘与巩固，在图像识别和自然语言处理持续学习基准测试中展现出比当代持续学习算法更优的迁移学习性能。