Neural nets do not need to be a black box: the recent mathematics of deep learning

Date: Tuesday, January 14th, 2025, 13:00-14:00 Cyprus Time. 

Venue:This training event is held as a hybrid event. You are welcome to join us at the Andreas Mouskos Auditorium, José Mariano Gago Hall, The Cyprus Institute. Otherwise please, connect to our live stream of the discussion, available on Zoom (Password: VsSCz1) 

Language: English 

Agenda

13:00 - 14:00

Prof. Constantine Dovrolis

Title: Neural nets do not need to be a black box: the recent mathematics of deep learning

Over the last decade, deep learning has evolved from being an enigmatic “black box” to a field where mathematics provide clear insights into its remarkable success. In this talk, we will explore how modern analysis has shed light on key questions, including:

1.    Why overparameterized neural networks generalize well (despite earlier results from classical learning theory).
2.    The critical role of depth in the neural network architecture.
3.    How deep learning avoids the curse of dimensionality.
4.    The surprising efficiency of optimization methods despite the non-convex nature of the problem.

Short bio:

Prof. Constantine Dovrolis is the Director of the center for Computational Science and Technology (CaSToRC) at The Cyprus Institute (CyI). He is also a Professor at the School of Computer Science at the Georgia Institute of Technology. His research is highly inter-disciplinary, combining Network Theory, Data Mining and Machine Learning. More recently, his group has been focusing on neuro-inspired architectures for machine learning based on what is currently known about the structure and function of brain networks.