ePoster · Machine Learning
A Study of a biologically plausible combination of Sparsity, Weight Imprinting and Forward Inhibition in Continual Learning
Golzar Atefi, Justus Westerhof, Felix Gers, Erik Rodner · Bernstein Conference 2024
Continual learning focuses on systems that incrementally acquire and update their knowledge. It is a pressing problem in machine learning as it is challenging to learn new tasks without forgetting knowledge about old ones, a phenomenon known as catastrophic forgetting [1]. Since biological systems are able to efficiently learn and update their knowledge continually during their lifetime, we are interested in principles inspired by these systems to try to tackle this challenge. One of the ideas in biology that is often overlooked in artificial neural networks is Dale’s principle [2], stating th