BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A categorical semantics for neural networks - Charlotte Aten\, Uni
 versity of Denver
DTSTART:20231124T140000Z
DTEND:20231124T150000Z
UID:TALK208831@talks.cam.ac.uk
CONTACT:Jamie Vicary
DESCRIPTION:In recent work on discrete neural networks\, I considered such
  networks whose activation functions are polymorphisms of finite\, discret
 e relational structures. The general framework I provided was not entirely
  categorical in nature but did provide a steppingstone to a categorical tr
 eatment of neural nets which are definitionally incapable of overfitting. 
 In this talk I will outline how to view neural nets as categories of funct
 ors from certain multicategories to a target multicategory. Moreover\, I w
 ill show that the results of my PhD thesis allow one to systematically def
 ine polymorphic learning algorithms for such neural nets in a manner appli
 cable to any reasonable (read: functorial) finite data structure.
LOCATION:Lecture Theatre 2\, Computer Laboratory
END:VEVENT
END:VCALENDAR