
This is the slides of the tutorial to be given by Yann LeCun
on December 4th 2006 at the NIPS 2006 conference in Vancouver:
Here is a link to the paper covering most of the material in the
tutorial:
 [LeCun et al. 2006]: A Tutorial on
EnergyBased Learning (in Bakir et al. (eds) "Predicting
Strutured Data", MIT Press 2006): This is a tutorial paper on
EnergyBased Models (EBM). Inference in EBMs consists in searching
for the value of the output variables that minimize an energy
function. Learning consists in shaping that energy function in such
a way that desired configuration have lower energy than undesired
ones. The EBM approach provides a common theoretical framework for
many probabilistic and nonprobabilistic learning models, including
traditional discriminative and generative approaches, as well as
graphtransformer networks, conditional random fields, maximum
margin Markov networks, and several manifold learning methods. Some
of the methods described in this paper help circumvent the problem
of evaluating partition functions that often plagues probabilistic
methods. Further information is available
here.  

