Talk title: Statistical Learning in Biological Neural Networks

Abstract: Compared to artificial neural networks (ANNs), the brain learns faster, generalizes better to new situations and consumes much less energy. ANNs are motivated by the functioning of the brain, but differ in several crucial aspects. In particular, it is biologically implausible that the learning of the brain is based on gradient descent. In this talk we look at the brain as a statistical method for supervised learning. The main contribution is to relate the local updating rule of the connection parameters in biological neural networks (BNNs) to a zero-order optimization method. The talk is based on arxiv:2301.11777.

Location: Vector MaRS MPRs. The speaker will present in person, thus in-person registration is highly recommended. A virtual Zoom link will also be provided after registration.

Lunch will be provided for registered in-person participants. Please RSVP by Sunday, August 6 to secure your spot! Capacity is limited, so register early to not miss out! 


Johannes Schmidt-Hieber, Professor of Statistics at the University of Twente.
Personal page:

This event is open to Vector Sponsors, Vector Researchers, and invited health partners only. Any registration that is found not to be a Vector Sponsor, Vector Researcher or invited health partner will be asked to provide verification and, if unable to do so, will not be able to attend the event. Please contact if you have any questions.