A categorical semantics for neural networks

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

• Charlotte Aten, University of Denver
• Friday 24 November 2023, 14:00-15:00
• Lecture Theatre 2, Computer Laboratory.

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

In recent work on discrete neural networks, I considered such networks whose activation functions are polymorphisms of finite, discrete relational structures. The general framework I provided was not entirely categorical in nature but did provide a steppingstone to a categorical treatment of neural nets which are definitionally incapable of overfitting. In this talk I will outline how to view neural nets as categories of functors from certain multicategories to a target multicategory. Moreover, I will show that the results of my PhD thesis allow one to systematically define polymorphic learning algorithms for such neural nets in a manner applicable to any reasonable (read: functorial) finite data structure.

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

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge talks
• Computing and Mathematics
• Department of Computer Science and Technology talks and seminars
• Interested Talks
• Lecture Theatre 2, Computer Laboratory
• Logic and Semantics Seminar (Computer Laboratory)
• School of Technology
• Trust & Technology Initiative - interesting events
• bld31
• yk373's list

Note that ex-directory lists are not shown.