Speaker: Ding-Xuan Zhou, The University of Sydney, School of Mathematics and Statistics
Title: "Mathematical theory of structured deep neural networks"
Abstract:
Deep learning has been widely applied and brought breakthroughs in speech recognition, computer vision, natural language processing, and many other domains. The involved deep neural network architectures and com-putational issues have been well studied in machine learning. But there is much less theoretical understanding about the modelling, approximation or generalization abilities of deep learning models with network architec-tures. Important families of structured deep neural networks include deep convolutional neural networks induced by convolutions and transformers by attentions. The architectures give essential differences between such struc-tured networks and fully-connected ones. This talk describes approximation and generalization analysis of deep convolutional neural networks and trans-formers.
Bio:
Ding-Xuan Zhou is Professor and Head of School of Mathematics and Statistics, University of Sydney. Before moving to Australia in 2022, he was a Chair Professor at City University of Hong Kong. His recent research is focused on theory of machine learning and deep neural networks. Due to his work on machine learning theory starting in 1999, he was rated in 2014-2017 by Thomson Reuters/Clarivate Analytics as a highly-cited researcher.
In person attendance at this seminar is only open to Columbia University affiliates. External guests are welcome to attend remotely. Please contact [email protected] if you need the Zoom link for this seminar.
