Talks.cam will close on 1 July 2026, further information is available on the UIS Help Site
 

University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Capitalizing Catastrophe Principle in Training Deep Neural Networks & Further Related Topics

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

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

Capitalizing Catastrophe Principle in Training Deep Neural Networks & Further Related Topics

Add to your list(s) Download to your calendar using vCal

  • UserChang-Han Rhee (Northwestern University)
  • ClockFriday 05 April 2024, 09:30-11:00
  • HouseExternal.

If you have a question about this talk, please contact nobody.

TMLW01 - SGD, stability and simulation in the presence of heavy tails

This talk is part of the Isaac Newton Institute Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Eurocrisis Conference 14-15 June streaming ITA Google is taking over

Other talks

The cacti and other attractions of Colorado Optimal approaches with Zig Fundamentals and Recent Advances in Controlled Radical Polymerization LMB Seminar: Biosynthesis and degradation of the underappreciated green polymer cyanophycin Introduction to statistical learning theory, SGD, neural networks Spatial causal inference in the presence of unmeasured confounding and interference
 

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