Uncertainty-guided Continual Learning with Bayesian Neural Networks

Sayna Ebrahimi
Sayna Ebrahimi
Marcus Rohrbach
Marcus Rohrbach

ICLR, 2020.

Cited by: 0|Bibtex|Views147
EI
Other Links: academic.microsoft.com|dblp.uni-trier.de|arxiv.org

Abstract:

Continual learning aims to learn new tasks without forgetting previously learned ones. This is especially challenging when one cannot access data from previous tasks and when the model has a fixed capacity. Current regularization-based continual learning algorithms need an external representation and extra computation to measure the param...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments