Context selectivity with dynamic availability enables lifelong continual learning
This work addresses the challenge of enabling AI systems to learn continuously without forgetting, which is incremental as it builds on classical continual learning principles.
The paper tackled the problem of lifelong continual learning by proposing a bio-plausible meta-plasticity rule based on neuron context selectivity and local availability, which balances forgetting and consolidation. In simulations, this model achieved better transfer learning than contemporary algorithms on image recognition and NLP benchmarks.
"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.