[HTML][HTML] Continual lifelong learning with neural networks: A review

GI Parisi, R Kemker, JL Part, C Kanan, S Wermter - Neural networks, 2019‏ - Elsevier
Humans and animals have the ability to continually acquire, fine-tune, and transfer
knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is …

Catastrophic forgetting, rehearsal and pseudorehearsal

A Robins - Connection Science, 1995‏ - Taylor & Francis
This paper reviews the problem of catastrophic forgetting (the loss or disruption of previously
learned information when new information is learned) in neural networks, and explores …

[PDF][PDF] Deep class-incremental learning: A survey

DW Zhou, QW Wang, ZH Qi, HJ Ye… - ar**
P Kaushik, A Gain, A Kortylewski, A Yuille - arxiv preprint arxiv …, 2021‏ - arxiv.org
Catastrophic forgetting in neural networks is a significant problem for continual learning. A
majority of the current methods replay previous data during training, which violates the …

Catastrophic forgetting in deep learning: a comprehensive taxonomy

EL Aleixo, JG Colonna, M Cristo… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Deep Learning models have achieved remarkable performance in tasks such as image
classification or generation, often surpassing human accuracy. However, they can struggle …