Variational Continual Learning
Abstract
This paper develops variational continual learning (VCL), a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks. The framework can successfully train both deep discriminative models and deep generative models in complex continual learning settings where existing tasks evolve over time and entirely new tasks emerge. Experimental results show that VCL outperforms state-of-the-art continual learning methods on a variety of tasks, avoiding catastrophic forgetting in a fully automatic way.
Cite
Text
Nguyen et al. "Variational Continual Learning." International Conference on Learning Representations, 2018.Markdown
[Nguyen et al. "Variational Continual Learning." International Conference on Learning Representations, 2018.](https://mlanthology.org/iclr/2018/nguyen2018iclr-variational/)BibTeX
@inproceedings{nguyen2018iclr-variational,
title = {{Variational Continual Learning}},
author = {Nguyen, Cuong V. and Li, Yingzhen and Bui, Thang D. and Turner, Richard E.},
booktitle = {International Conference on Learning Representations},
year = {2018},
url = {https://mlanthology.org/iclr/2018/nguyen2018iclr-variational/}
}