Login with HarvardKey to view all events.

Tackling the Complexity of Modern Machine Learning

This is a past event.

Thursday, April 14, 2022 12pm to 1pm

Fashion by Marina Debris

Event Dates

Thursday, April 14, 2022 12pm to 1pm

Add to calendar

Deep neural networks are a rich family of function approximators ubiquitous across many domains leveraging machine learning. Our understanding of their function, design, and limitations, however, is less well-developed. Can we quantitatively characterize the important aspects of deep learning and develop an understanding of its complex design space? In this talk, I describe some of my research in building foundations for deep learning based on three related threads. First, I describe exact connections between deep neural networks, in the limit of infinitely-wide hidden layers, with new classes of Gaussian processes and kernel methods. Second, I discuss an equivalence between wide, deep neural networks and linear models as well as characterize a nonlinear regime where the equivalence breaks. Third, I discuss scaling trends for the performance of supervised deep learning in practice. Building off of these threads, I highlight areas for further research in core machine learning as well as a few promising application areas for machine learning in physical science.

Event Details