Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy
Journal of the Brazilian Computer Society · 06.08.2024 · 30 (1)
DOI: 10.5753/jbcs.2024.3966 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Brazilian Computer Society, online erschienen am 06.08.2024. Verfasst von Everton Lima Aleixo und 3 weiteren Autor:innen. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 204 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Deep Learning models have achieved remarkable performance in tasks such as image classification or generation, often surpassing human accuracy. However, they can struggle to learn new tasks and update their knowledge without access to previous data, leading to a significant loss of accuracy known as Catastrophic Forgetting (CF). This phenomenon was first observed by McCloskey and Cohen in 1989 and remains an active research topic. Incremental learning without forgetting is widely recognized as a crucial aspect in building better AI systems, as it allows models to adapt to new tasks without losing the ability to perform previously learned ones. This article surveys recent studies that tackle CF in modern Deep Learning models that use gradient descent as their learning algorithm. Although several solutions have been proposed, a definitive solution or consensus on assessing CF is yet to be established. The article provides a comprehensive review of recent solutions, proposes a taxonomy to organize them, and identifies research gaps in this area.
Zitieren
APA
Aleixo, E. L., Colonna, J. G., Cristo, M., & Fernandes, E. (2024). Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy. Journal of the Brazilian Computer Society, 30(1). https://doi.org/10.5753/jbcs.2024.3966
Vancouver
Aleixo EL, Colonna JG, Cristo M, Fernandes E. Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy. Journal of the Brazilian Computer Society. 2024;30(1). doi:10.5753/jbcs.2024.3966
BibTeX
@article{Aleixo2024,
author = {Aleixo, Everton Lima and Colonna, Juan G. and Cristo, Marco and Fernandes, Everlandio},
title = {Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy},
journal = {Journal of the Brazilian Computer Society},
year = {2024},
volume = {30},
number = {1},
doi = {10.5753/jbcs.2024.3966}
}
EUVIMED