Machine Learning Seminar: Zhou -- Mathematical theory of structured deep neural networks

The details about the machine learning seminar are as follows: 

Time: Mon 23 March (1:00 - 2:00pm): 

Location: SMRI Seminar Room (A12-03-301) A12 Macleay Building, Level 3, Room 301.  

Speaker: Dingxuan Zhou (USYD) 

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 computational
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 architectures.
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 structured
networks and fully-connected ones. This talk describes some approximation
and generalization analysis of deep convolutional neural networks and
transformers.