BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Connections between kernels\, GPs\, and NNs - Matthias Bauer (Univ
 ersity of Cambridge)\; Paul Rubenstein
DTSTART:20151112T143000Z
DTEND:20151112T160000Z
UID:TALK62018@talks.cam.ac.uk
CONTACT:Yingzhen Li
DESCRIPTION:First\, we will follow Radford Neal's PhD thesis and explain t
 hat an infinite Neural Network with random weights is equivalent to a GP. 
 We will then look at several examples of Neural Network kernels and discus
 s their properties.\n\nIn the second part\, we are going to talk about GPs
  and Kernels in the context of regression. We will derive Kernel Ridge Reg
 ression and show that it is equivalent to MAP inference in a GP regression
  model. Along the way we will give a brief introduction to the theory of R
 eproducing Kernel Hilbert Spaces. \nTime permitting\, we will end by intro
 ducing Support Vector Regression - another Kernel regression technique\, b
 ut one that cannot be viewed as performing MAP inference in any GP model.\
 n\nThere is no required reading. However\, if you want to read something\,
  feel free to look at Chapter 2 of Radford Neal's thesis. \n"html":http://
 www.cs.toronto.edu/~radford/thesis.abstract.html \n"pdf":http://www.cs.tor
 onto.edu/~radford/ftp/pin.pdf
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR