I don't expect the talk to be more than say 20 minutes as I only intend to give an overview of the paper. Any additional time would come from whatever discussion arises.


On Mon, Jul 14, 2014 at 2:09 PM, Yoshua Bengio <yoshua.bengio@gmail.com> wrote:

It's Nicolas Boulanger's PhD defense at 2pm. Make sure the tea talk is short.

Yoshua

On Jul 14, 2014 1:51 PM, "Kyung Hyun Cho" <cho.k.hyun@gmail.com> wrote:
Dear all,

This Friday at 13.00, Dustin will give a tea talk about building a deep/multilayer kernel based on the paper <Kernel Methods for Deep Learning> by Youngmin Cho and Lawrence K. Saul presented earlier at NIPS 2009.

Note that the place is not the usual lecture hall in the same building, but is Z-209 in the neighbouring building (Pavillon Claire-McNicoll).

Hope to see many of you on Friday!
- Cho

====

- Speaker: Dustin Webb (University of Utah)
- Date and Time: 13 July 2014 @13.00
- Place: Z-209
- Abstract:

We introduce a new family of positive-deļ¬nite kernel functions that mimic the
computation in large, multilayer neural nets. These kernel functions can be used
in shallow architectures, such as support vector machines (SVMs), or in deep
kernel-based architectures that we call multilayer kernel machines (MKMs). We
evaluate SVMs and MKMs with these kernel functions on problems designed to
illustrate the advantages of deep architectures. On several problems, we obtain
better results than previous, leading benchmarks from both SVMs with Gaussian
kernels as well as deep belief nets.

http://cseweb.ucsd.edu/~saul/papers/nips09_kernel.pdf

_______________________________________________
Lisa_labo mailing list
Lisa_labo@iro.umontreal.ca
https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_labo


_______________________________________________
Lisa_labo mailing list
Lisa_labo@iro.umontreal.ca
https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_labo




--
Dustin Webb
Algorithmic Robotics Lab
Laboratoire d'Informatique des Systemes Adaptatifs
Defining Intelligence