Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence

by   Liyuan Wang, et al.

Continual learning aims to empower artificial intelligence (AI) with strong adaptability to the real world. For this purpose, a desirable solution should properly balance memory stability with learning plasticity, and acquire sufficient compatibility to capture the observed distributions. Existing advances mainly focus on preserving memory stability to overcome catastrophic forgetting, but remain difficult to flexibly accommodate incremental changes as biological intelligence (BI) does. By modeling a robust Drosophila learning system that actively regulates forgetting with multiple learning modules, here we propose a generic approach that appropriately attenuates old memories in parameter distributions to improve learning plasticity, and accordingly coordinates a multi-learner architecture to ensure solution compatibility. Through extensive theoretical and empirical validation, our approach not only clearly enhances the performance of continual learning, especially over synaptic regularization methods in task-incremental settings, but also potentially advances the understanding of neurological adaptive mechanisms, serving as a novel paradigm to progress AI and BI together.


page 10

page 11

page 42


Sustainable Artificial Intelligence through Continual Learning

The increasing attention on Artificial Intelligence (AI) regulation has ...

Understanding Regularisation Methods for Continual Learning

The problem of Catastrophic Forgetting has received a lot of attention i...

Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning

Continual learning is considered a promising step towards next-generatio...

Reviewing continual learning from the perspective of human-level intelligence

Humans' continual learning (CL) ability is closely related to Stability ...

CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One

Continual learning requires incremental compatibility with a sequence of...

Prospective Learning: Back to the Future

Research on both natural intelligence (NI) and artificial intelligence (...

Towards a theory of out-of-distribution learning

What is learning? 20^st century formalizations of learning theory – whic...

Please sign up or login with your details

Forgot password? Click here to reset