Keynote Lecture: Andrew Saxe

What does deep learning imply about cognition?

Andrew Saxe, University College London
Henry Dale Fellow and Joint Group Leader at the
Gatsby Computational Neuroscience Unit and Sainsbury Wellcome Centre

The brain is an unparalleled learning machine, yet the principles that govern learning in the brain remain unclear. In this talk I will suggest that depth–the serial propagation of signals–may be a key principle sculpting learning dynamics in the brain and mind. To understand several consequences of depth, I will present mathematical analyses of the nonlinear dynamics of learning in simple solvable deep network models. Building from this theoretical work, I will turn to experiments in rodents and humans, showing how these principles play out in diverse aspects of cognition. Together, these results provide analytic insight into how the statistics of an environment interact with network architecture and learning rules to structure evolving neural representations and behavior over learning.