Continual Learning With Speculative Backpropagation and Activation History

Continual learning is gaining traction these days with the explosive emergence of deep learning applications. Continual learning suffers from a severe problem called catastrophic forgetting. It means that the trained model loses the previously learned information when training with new data. This pa...

Full description

Bibliographic Details

Published in:	IEEE Access
Main Authors:	Sangwoo Park, Taeweon Suh
Format:	Article
Language:	English
Published:	IEEE 2022-01-01
Subjects:	Continual learning lifelong learning catastrophic forgetting parallel training speculative backpropagation activation history
Online Access:	https://ieeexplore.ieee.org/document/9754561/