Embracing Change: Continual Learning in Deep Neural Networks
Citations Over TimeTop 1% of 2020 papers
Abstract
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 systems do, from a continuous stream of correlated data. In the present review, we relate continual learning to the learning dynamics of neural networks, highlighting the potential it has to considerably improve data efficiency. We further consider the many new biologically inspired approaches that have emerged in recent years, focusing on those that utilize regularization, modularity, memory, and meta-learning, and highlight some of the most promising and impactful directions.
Related Papers
- → An a posteriori measure of network modularity(2013)11 cited
- → An a posteriori measure of network modularity(2013)7 cited
- → Skin Disease Diagnostic techniques using deep learning(2022)2 cited
- Modified modularity and the corresponding community structure detecting algorithm(2010)
- → Security Through Modularity(2019)