Achieving Deep Continual Learning via Evolution
This addresses the challenge of continual learning for AI systems, offering a novel collective approach rather than incremental improvements to single models.
The paper tackles the problem of deep continual learning by introducing Evolving Continual Learning (ECL), a framework that evolves a population of neural network models to create task-specific experts, and it significantly outperforms state-of-the-art methods.
Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL). While most current methods aim to enhance the capabilities of a single model, Inspired by the collective learning mechanisms of human populations, we introduce Evolving Continual Learning (ECL), a framework that maintains and evolves a diverse population of neural network models. ECL continually searches for an optimal architecture for each introduced incremental task. This tailored model is trained on the corresponding task and archived as a specialized expert, contributing to a growing collection of skills. This approach inherently resolves the core CL challenges: stability is achieved through the isolation of expert models, while plasticity is greatly enhanced by evolving unique, task-specific architectures. Experimental results demonstrate that ECL significantly outperforms state-of-the-art individual-level CL methods. By shifting the focus from individual adaptation to collective evolution, ECL presents a novel path toward AI systems capable of CL.