The VI AMMCS International Conference

Waterloo, Ontario, Canada | August 14-18, 2023

AMMCS 2023 Plenary Talk

Theories of Deep Learning

Clayton Scott (University of Michigan, Ann Arbor)

Over the past decade, deep neural networks have brought about major advances in computer vision, natural language modeling, protein structure prediction, and several other applications. These neural networks succeed despite having far more model parameters than training data. Classical machine learning theory suggests that overparametrized models will overfit, and cannot explain deep networks' low generalization error. In this talk I will survey recent theoretical developments that seek to better explain the performance of deep learning models, and present new results on the generalization ability of quantized neural networks and interpolating predictors.
Clay Scott received his PhD and MS in Electrical Engineering from Rice University in 2004 and 2000, and his AB in Mathematics from Harvard in 1998. He is currently Professor of Electrical Engineering and Computer Science, and of Statistics, at the University of Michigan. His research interests include statistical machine learning theory and algorithms, with an emphasis on nonparametric methods for supervised and unsupervised learning. He has also worked on a number of applications including brain imaging, nuclear threat detection, environmental monitoring, and computational biology. In 2010, he received the Career Award from the National Science Foundation.