Find last information on: www.ijcai.org   ,   www.ijcai-21.org   and   www.ijcai-22.org Home
IJCAI-05

Nineteenth International Joint Conference on Artificial Intelligence
EDINBURGH, SCOTLAND     30 JULY - 5 AUGUST 2005

schedule | papers | posters | tutorials | workshops | exhibition | nmpl-texas | sponsors

welcome | contact | speakers | meetings | pc | advisory | organisers | social | map | info | colocating

Research Excellence Lecture

Prof Geoffrey Hinton
Canadian Institute for Advanced Research &
University of Toronto

What Kind of a Graphical Model is the Brain?

If neurons are treated as latent variables, our visual systems are non-linear, densely-connected graphical models containing billions of variables and thousands of billions of parameters. Current algorithms would have difficulty learning a graphical model of this scale. Starting with an algorithm that has difficulty learning more than a few thousand parameters, I describe a series of progressively better learning algorithms all of which are designed to run on neuron-like hardware. The latest member of this series can learn deep, multi-layer belief nets quite rapidly. It turns a generic network with three hidden layers and 1.7 million connections into a very good generative model of hand-written digits. After learning, the model gives classification performance that is comparable to the best discriminative methods.

For Prof Hinton's biography, see the IJCAI Awards page

 

Last updated: 07 September 2005

info@ijcai-05.org

schedule | papers | posters | tutorials | workshops | exhibition | nmpl-texas | sponsors

welcome | contact | speakers | meetings | pc | advisory | organisers | social | map | info | colocating