University of Cambridge > Talks.cam > Logic and Semantics Seminar (Computer Laboratory) > Categorical Foundations of Gradient-Based Learning

Categorical Foundations of Gradient-Based Learning

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

  • UserFabio Zanasi, UCL
  • ClockFriday 04 February 2022, 14:00-15:00
  • HouseFW26.

If you have a question about this talk, please contact Jamie Vicary.

THIS TALK WILL BE IN SS03 , NOT FW26

I will present recent work (joint with G. Cruttwell, B. Gavranovic, N. Ghani, and P. Wilson) on providing semantic foundations to machine learning using the tools of logic, algebra and category theory. This framework provides a much needed unifying perspective on different training techniques for machine learning models, based on the categorical notion of lens. This abstract viewpoint does not only allow to study uniformly learning with neural networks, but also to extend these techniques to other, previously unexplored models, such as Boolean circuits.

This talk is part of the Logic and Semantics Seminar (Computer Laboratory) series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2022 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity