BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Philipp Misof
DTSTART:20250416T143000Z
DTEND:20250416T150000Z
DTSTAMP:20260423T040037Z
UID:gbgphd/11
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/gbgphd/11/">
 The rotation-symmetric spherical cow of Deep Learning $\\rightarrow$ Wide 
 Learning</a>\nby Philipp Misof as part of Gothenburg PhD seminar\n\nLectur
 e held in MVL14.\n\nAbstract\nDue to the current boom in AI\, deep learnin
 g has become mainstream. The name is inspired by the fact that the corresp
 onding machine learning models are usually a composition of many layers of
  parametrized transformations. To swim against (or arguably orthogonal to)
  the tide\, what happens if we instead consider particularly 𝘸𝘪𝘥
 𝘦 layers? In this talk\, I will present the spherical cow equivalent of
  neural networks and how this spherical cow can even be endowed with addit
 ional symmetry\, like 3d rotations (... the analogy may be lacking).\n
LOCATION:https://researchseminars.org/talk/gbgphd/11/
END:VEVENT
END:VCALENDAR