The IEEE Washington Section calendar pulls content from both the Washington Section's vTools Events feed and the Northern Virginia Section's vTools Events feed, since there is significant overlap between the two sections' members. (vTools Events is the IEEE-operated database that contains all IEEE events globally. To be useful, it requires filtering at the section level.)

Registration for events is handled by vTools. To register for an event using vTools, click the “Register Today” link at the bottom of an event description on this site.

All major Region 2 conferences and events are provided on the IEEE conferences page. Select the date range and/or state within Region 2 to find relevant conferences or events.

Loading Events

« All Events

  • This event has passed.

When Harmonic Analysis meets Machine Learning: Lipschitz Analysis of Deep Convolution Networks

October 10 @ 18:30 - 20:30

Co-sponsored by: WASH Signal Processing Society

Deep neural networks have led to dramatic improvements in performance for many machine learning tasks, yet the mathematical reasons for this success remain largely unclear. In this talk we present recent developments in the mathematical framework of convolutive neural networks (CNN). In particular we discuss the scattering network of Mallat and how it relates to another problem in harmonic analysis, namely the phase retrieval problem. Then we discuss the general convolutive neural network from a theoretician point of view. We present Lipschitz analysis results using two analytical methods: the chain rule (or backpropagation) and the storage function method inspired by Mallat’s scattering network analysis. Towards the end of the talk we discuss how these theoretical results can be applied in practice, and in particular we mention various design methods that incorporate Lipschitz bounds as penalty terms into optimization problems.

Speaker(s): Prof. Radu Balan,

Agenda:

Light dinner and refreshments will be served at 6:30pm; lecture will start at 7pm. 

If arriving by car, feel free to use parking lot 11b, which is open for general access after 4pm. If arriving by Metro, free shuttle service is available from the College Park station to campus. 

Location:
Room: 2460 (ECE Department’s Colloquium Room)
Bldg: AV Williams – Parking Lot 11B
University of Maryland
College Park, Maryland

Details

Date:
October 10
Time:
18:30 - 20:30
Website:
Register today!