On Sequential Bayesian Inference for Continual Learning

On Sequential Bayesian Inference for Continual Learning

Sequential Bayesian inference can be used for <i>continual learning</i> to prevent catastrophic forgetting of past tasks and provide an informative prior when learning new tasks. We revisit sequential Bayesian inference and assess whether using the previous task’s posterior as a prior fo...

Full description

Bibliographic Details
Main Authors: Samuel Kessler, Adam Cobb, Tim G. J. Rudner, Stefan Zohren, Stephen J. Roberts
Format: Article
Language:English
Published: MDPI AG 2023-05-01
Series:Entropy
Subjects:
continual learning
lifelong learning
sequential Bayesian inference
Bayesian deep learning
Bayesian neural networks
Online Access:https://www.mdpi.com/1099-4300/25/6/884

Internet

https://www.mdpi.com/1099-4300/25/6/884

Similar Items