Embracing Change: Continual Learning in Deep Neural Networks

• Published in: Trends in cognitive sciences Vol. 24; no. 12; pp. 1028 - 1040
• Main Authors: Hadsell, Raia, Rao, Dushyant, Rusu, Andrei A., Pascanu, Razvan
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.12.2020
• Subjects: Artificial Intelligence; Humans; Learning; lifelong; Memory; meta-learning; Neural Networks, Computer; non-stationary; non-stationary; memory; lifelong; meta-learning; artificial intelligence

Artificial intelligence research has seen enormous progress over the past few decades, but it predominantly relies on fixed datasets and stationary environments. Continual learning is an increasingly relevant area of study that asks how artificial systems might learn sequentially, as biological syst...