Learning and generalisation of task knowledge in humans and neural networks

There has been a renaissance of interest in connectionist networks as models of biological computation. During sensory perception, deep neural networks learn representations that resemble those in primate neocortex. However, neural networks learn to perform and generalise cognitive tasks in very different ways to people. In my talk, I will explore these differences, and suggest computational adaptations that allow neural networks to learn multiple tasks in series, reconfigure task knowledge from limited data, and generalise knowledge between tasks.

To meet Christopher Summerfield, please contact Magdalena Soukupova: magdalena.soukupova@ens.fr

The nEuro-economics seminar series is organised by the Human Reinforcement Learning team directed by Stefano Plaminteri at the LNC2.