A two-day summit of talks, activities, and workshops

To contribute a talk or to receive the zoom information of this workshop, please register for this workshop.

Day 1

Day 1 focuses on the approximation and generalization theory of deep neural networks. You will understand why deep neural networks are powerful and how powerful they would be (i.e., the limitation), especially for learning high-dimensional functions! You will understand how to interpret deep learning instead of treating it as a black-box!

Day 2

Day 2 focuses on the optimization theory and algorithms of deep learning with applications to various mathematical problems in science and engineering. You will understand why deep learning works so well with simple optimization algorithms for various data sets! You will understand how to apply deep learning in mathematical problems through the exciting examples in our invited talks!

The goal of this event is to stimulate collaborative efforts to advance scientific machine learning and its theoretical foundation.

What starts here may change your understanding of deep learning. Present, discuss, and collaborate!

Invited Speakers

California Institute of Technology

Sandia National Laboratories

Texas A&M University

Columbia University

Brown University

University of Chicago

Ludwig Maximilian University of Munich

Princeton University

Duke University

Stanford University

University of California, Los Angeles

National University of Singapore

Columbia University

Pennsylvania State University

Stanford University

University of California, Berkeley

The Venue

Zoom link to be announced on August 10, 2021

Let us know if you'll be attending!

This workshop is jointly supported by Institute for Mathematics and its Applications and the Department of Mathematics at Purdue University