Dr Cuong Nguyen viet.c.nguyen@durham.ac.uk
Assistant Professor
Dr Cuong Nguyen viet.c.nguyen@durham.ac.uk
Assistant Professor
Siddharth Swaroop
Thang D. Bui
Yingzhen Li
Richard E. Turner
Xiaoli Li
Editor
Savitha Ramasamy
Editor
ArulMurugan Ambikapathi
Editor
Suresh Sundaram
Editor
Haytham M Fayek
Editor
This chapter describes a general Bayesian framework for the lifelong learning of artificial neural networks that can handle catastrophic forgetting in a principled way. The framework can be applied to both discriminative and generative models as well as task-aware and task-agnostic settings. We introduce the variational continual learning algorithm, a realization of this framework that uses online variational inference with a small amount of memory or coreset for effective lifelong learning. We examine various practical considerations when using this algorithm and show that it performs competitively against other lifelong learning approaches on different benchmarks. We also discuss several improvements to the algorithm and outline some future research directions for Bayesian lifelong learning.
Nguyen, C. V., Swaroop, S., Bui, T. D., Li, Y., & Turner, R. E. (2024). Lifelong Learning for Deep Neural Networks with Bayesian Principles. In X. Li, S. Ramasamy, A. Ambikapathi, S. Sundaram, & H. M. Fayek (Eds.), Towards Human Brain Inspired Lifelong Learning (51-72). World Scientific Publishing. https://doi.org/10.1142/9789811286711_0004
Online Publication Date | Apr 24, 2024 |
---|---|
Publication Date | 2024-05 |
Deposit Date | Jun 3, 2024 |
Publicly Available Date | Apr 25, 2025 |
Publisher | World Scientific Publishing |
Pages | 51-72 |
Book Title | Towards Human Brain Inspired Lifelong Learning |
Chapter Number | 4 |
ISBN | 9789811286704 |
DOI | https://doi.org/10.1142/9789811286711_0004 |
Public URL | https://durham-repository.worktribe.com/output/2472032 |
This file is under embargo until Apr 25, 2025 due to copyright restrictions.
Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient
(2025)
Presentation / Conference Contribution
The Matter of Captchas: An Analysis of a Brittle Security Feature on the Modern Web
(2024)
Presentation / Conference Contribution
Simple transferability estimation for regression tasks
(2023)
Presentation / Conference Contribution
Bayesian active learning with abstention feedbacks
(2021)
Journal Article
About Durham Research Online (DRO)
Administrator e-mail: dro.admin@durham.ac.uk
This application uses the following open-source libraries:
Apache License Version 2.0 (http://www.apache.org/licenses/)
Apache License Version 2.0 (http://www.apache.org/licenses/)
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2025
Advanced Search