Neural networks can achieve human-like performance on sensory and cognitive tasks through adjustment of their connections. The link between these connections and neural computation, however, remains unclear. Random graph theory provides powerful descriptions of network structure and dynamics, and the mathematics of random graphs provides a useful tool in understanding computation in biological and artificial neural networks. This seminar series will bring together leading researchers studying neural dynamics, computation, and the mathematics of random graphs. This diverse group of outstanding researchers represents an opportunity to create links and foster new approaches in discrete mathematics and neural computation. Monthly virtual talks (second Thursdays of each month, 12-1 PM EST) will aim to create new discussions and collaborations.

*Please note this lecture series continues to the end of 2021, dates from July onward can be found here*

Confirmed speakers title/abstract submission.