skip to content

Approximation via Deep Neural Networks

Presented by: 
Guergana Petrova
Friday 7th June 2019 - 14:00 to 15:00
INI Seminar Room 2
We will discuss the approximation power of deep neural networks.
In particular, we will present classes of functions which can be
efficiently captured by neural networks where classical nonlinear methods
fall short of the task.

University of Cambridge Research Councils UK
    Clay Mathematics Institute London Mathematical Society NM Rothschild and Sons