Context selectivity with dynamic availability enables lifelong continual learning

Abstract

"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.

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Overcoming catastrophic forgetting in neural networks
• A continual learning survey: Defying forgetting in classification tasks
• Progressive Neural Networks
• Bayesian Online Changepoint Detection
• Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization
• Reinforced Continual Learning
• Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments
• Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
• Constrained Predictive Coding as a Biologically Plausible Model of the Cortical Hierarchy
• Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping