Incorporating neuro-inspired adaptability for continual learning in artificial intelligence

By Liyuan Wang, Xingxing Zhang, Qian Li, Mingtian Zhang, Hang Su, Jun Zhu, Yi Zhong. 2023

101 citations recorded by the source corpus.

Continual learning aims to empower artificial intelligence 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 it remains difficult to flexibly accommodate incremental changes as biological intelligence does. Here, by modelling a robust Drosophila learning system that actively regulates forgetting with multiple learning modules, 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 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. Continual learning is an innate ability in biological intelligence to accommodate real-world changes, but it remains challenging for artificial intelligence. Wang, Zhang and colleagues model key mechanisms of a biological learning system, in particular active forgetting and parallel modularity, to incorporate neuro-inspired adaptability to improve continual learning in artificial intelligence systems.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Meta & Continual Learning, Neuroscience

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Rongwu Xu
2. Zehan Qi
3. Liyuan Wang
4. Hongru Wang
5. Hongwei Yan
6. Wei Xu
7. Kaisheng Ma
8. Yi Zhong

In Computer Vision and Pattern Recognition

1. Liyuan Wang
2. Hongwei Yan
3. Kaisheng Ma
4. Yi Zhong
5. Zhijiang Guo
6. Cunxiang Wang

In Meta & Continual Learning

1. Liyuan Wang
2. Hongwei Yan
3. Kaisheng Ma
4. Yi Zhong

Citations in the corpus

• A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, neutral): “2(e)), i.e., ∪ kt =1 θ t = ∅ , the generalization bounds are further refined by assuming K parameter spaces ( K ≥ 1 in general) to capture all tasks [69], [103].”
• Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation (2024, methodology): “Architecture-based methods focus on allocating dedicated parameter subspace, including parameter isolation [50, 68], dynamic architecture [17, 46, 59, 65], and modular network [62, 64].”
• Knowledge Conflicts for LLMs: A Survey (2024, background): “These findings underscore the need for further research into the interaction between parametric and contextual knowledge for LLMs.”