University of Cambridge > Talks.cam > Information Engineering Distinguished Lecture Series > A mathematical theory of deep neural networks

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

A mathematical theory of deep neural networks

Download to your calendar using vCal

If you have a question about this talk, please contact Prof. Ramji Venkataramanan .

Postponed due to COVID-19

During the past decade deep neural networks have led to spectacular successes in a wide range of applications such as image classification and annotation, handwritten digit recognition, speech recognition, and game intelligence. In this talk, we describe efforts to develop a mathematical theory that can explain these impressive practical achievements and possibly guide future deep learning architectures and algorithms. Specifically, we develop the fundamental limits of learning in deep neural networks by characterizing what is possible in principle. We then attempt to explain the inner workings of deep generative networks and of scattering networks. A brief survey of recent results on deep networks as solution engines for PDEs is followed by considerations of interesting open problems and philosophical remarks on the role of mathematics in AI research.

This talk is part of the Information Engineering Distinguished Lecture Series series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

GN06, William Gates Building and on Zoom: https://cam-ac-uk.zoom.us/j/88158575361 Faculty of English, 9 West Road, CB3 9DP: Room GR06/07 Fisher Building - St John's College

Other talks

Optimal metric and approximation of free boundary minimal surfaces The elephant in the room: Machine Learning directly into physical models The Gardens of the Western Cape Afternoon Break Group Presentation 5 TBC
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity