Meta-Consolidation for Continual Learning

Joseph K J; Vineeth N Balasubramanian

NeurIPS 2020poster60 citations

Meta-Consolidation for Continual Learning

Abstract

The ability to continuously learn and adapt itself to new tasks, without losing grasp of already acquired knowledge is a hallmark of biological learning systems, which current deep learning systems fall short of. In this work, we present a novel methodology for continual learning called MERLIN: Meta-Consolidation for Continual Learning.

BibTeX

@inproceedings{NEURIPS2020_a5585a4d,
 author = {K J, Joseph and N Balasubramanian, Vineeth},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
 pages = {14374--14386},
 publisher = {Curran Associates, Inc.},
 title = {Meta-Consolidation for Continual Learning},
 url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/a5585a4d4b12277fee5cad0880611bc6-Paper.pdf},
 volume = {33},
 year = {2020}
}