IMA Workshop on the Mathematical Foundation and Applications of Deep Learning
August 12 – 13, 2021
Hosted by Department of Mathematics
Co-Organized by Greg Buzzard, Guang Lin and Haizhao Yan
Deep learning has demonstrated remarkable, high-fidelity performance on computer vision and natural language processing tasks leading to significant improvement of industrial products such as automatic face and object recognition, self-driving cars, efficient ranking and recommendation systems over vast databases, etc. New branches in scientific discovery and computing have also emerged based on deep learning. The tremendous success of deep learning gives rise to numerous mathematical and algorithmic challenges related to a deeper understanding of new phenomena in machine learning. The goal of our workshop is to bring together computer scientists, applied mathematicians, and statisticians interested in the theoretical foundation of deep learning and applications to cross-fertilize ideas from multiple areas, including approximation theory, optimization methods, generalization performance, geometry analysis, and interpretability analysis. The talks will reflect the collaborative, multi- faceted nature of the mathematical theory of deep neural networks and their applications.
Please see more information on our webpage.
You are very welcome to join us in this virtual workshop!