Comparing continual task learning in minds and machines
Timo Flesch, Jan Balaguer, Ronald Dekker, Hamed Nili, Christopher Summerfield
Proceedings of the National Academy of Sciences10/15/2018·DOI·Read paper
Abstract
<jats:title>Significance</jats:title>
<jats:p>Humans learn to perform many different tasks over the lifespan, such as speaking both French and Spanish. The brain has to represent task information without mutual interference. In machine learning, this “continual learning” is a major unsolved challenge. Here, we studied the patterns of errors made by humans and state-of-the-art neural networks while they learned new tasks from scratch and without instruction. Humans, but not machines, seem to benefit from training regimes that blocked one task at a time, especially when they had a prior bias to represent stimuli in a way that encouraged task separation. Machines trained to exhibit the same prior bias suffered less interference between tasks, suggesting new avenues for solving continual learning in artificial systems.</jats:p>
Make this part of your paper trail
Save this paper to a shelf, write a review, and keep your own notes.