BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Kamal Diki (Chapman University)
DTSTART:20210917T220000Z
DTEND:20210917T230000Z
DTSTAMP:20260423T004659Z
UID:ags/8
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/ags/8/">An a
 pproach to the Gaussian RBF kernels via Fock spaces</a>\nby Kamal Diki (Ch
 apman University) as part of Analysis and Geometry Seminar\n\n\nAbstract\n
 In this talk we use methods from the Fock spaces theory in order to prove 
 several results on the Gaussian RBF kernels in the complex case. The latte
 r is one of the most used kernels in modern machine learning kernel method
 s\, and support vector machines (SVMs) classification algorithms. It turns
  out that complex analysis techniques allow us to consider several notions
  linked to the RBF kernels like the feature space and the feature map\, us
 ing the so-called Segal-Bargmann transform. We show also that the RBF kern
 els can be related to some important operators in quantum mechanics and ti
 me frequency analysis\, specifically\, we prove different connections of s
 uch kernels with creation\, annihilation\, Fourier\, translation\, modulat
 ion and Weyl operators. A semi-group property will be proved in the case o
 f Weyl operators. This is a joint work with Daniel Alpay\, Fabrizio Colomb
 o and Irene Sabadini.\n
LOCATION:https://researchseminars.org/talk/ags/8/
END:VEVENT
END:VCALENDAR