Humans and neural networks show similar patterns of transfer and interference during continual learning

Abstract excerpt

<p>Learning multiple tasks in succession is a challenge for artificial and biological agents alike. However, it is often claimed that artificial agents fail to learn new tasks without overwriting previous ones, while humans succeed. Here, using a canonical sequential rule-learning task in which learners acquire Task~A, then learn Task~B, and are finally re-tested on Task~A, we see conserved patterns of transfer an...

Topics

Open a Topic to create a Post that cites this publication.

• Cognition
• Eye Movements
• Models, Statistical
• Probability
• Proportional Hazards Models
• Psychomotor Performance
• Reaction Time
• Vision, Ocular

Identifiers and source

Literature Corpus work

471dbe5b-2d76-59ad-baec-bfacac02d3aa

DOI

10.31234/osf.io/98ksw_v1