Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

16

NIPS
2004

favoriteEmaildiscussreport

113views Information Technology» more NIPS 2004»

The Convergence of Contrastive Divergences

13 years 5 months ago

The Convergence of Contrastive Divergences

Download books.nips.cc

This paper analyses the Contrastive Divergence algorithm for learning statistical parameters. We relate the algorithm to the stochastic approximation literature. This enables us to specify conditions under which the algorithm is guaranteed to converge to the optimal solution (with probability 1). This includes necessary and sufficient conditions for the solution to be unbiased.

Alan L. Yuille

Real-time Traffic

Contrastive Divergence Algorithm | NIPS 2004 | NIPS 2007 | Statistical Parameters | Stochastic Approximation Literature |

claim paper

Related Content

» On the Convergence Properties of Contrastive Divergence

» Learning with Blocks Composite Likelihood and Contrastive Divergence

» Training restricted Boltzmann machines using approximations to the likelihood gradient

» Particle Filtered MCMCMLE with Connections to Contrastive Divergence

» Minimising Contrastive Divergence in Noisy Mixedmode VLSI Neurons

» Using fast weights to improve persistent contrastive divergence

» Wormholes Improve Contrastive Divergence

» Contrastive Divergence in Gaussian Diffusions

» Training Products of Experts by Minimizing Contrastive Divergence

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2004
Where	NIPS
Authors	Alan L. Yuille

Comments (0)