Unsupervised (parameter) learning for MRFs on bipartite graphs

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00212637" target="_blank" >RIV/68407700:21230/13:00212637 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.5244/C.27.72" target="_blank" >http://dx.doi.org/10.5244/C.27.72</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.5244/C.27.72" target="_blank" >10.5244/C.27.72</a>

Result language
angličtina
Original language name
Unsupervised (parameter) learning for MRFs on bipartite graphs
Original language description
We consider unsupervised (parameter) learning for general Markov random fields on bipartite graphs. This model class includes Restricted Boltzmann Machines. We show that besides the widely used stochastic gradient approximation (a.k.a. Persistent Con- trastive Divergence) there is an alternative learning approach - a modified EM algorithm which is tractable because of the bipartiteness of the model graph. We compare the re- sulting double loop algorithm and the PCD learning experimentally and show thatthe former converges faster and more stable than the latter.
Czech name
—
Czech description
—

Project
<a href="/en/project/GAP202%2F12%2F2071" target="_blank" >GAP202/12/2071: Structured Statistical Models for Image Understanding</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
BMVC2013: Proceedings of the British Machine Vision Conference
ISBN
1-901725-49-9
ISSN
—
e-ISSN
—
Number of pages
11
Pages from-to
"72.1"-"72.11"
Publisher name
British Machine Vision Association
Place of publication
London
Event location
Bristol
Event date
Sep 9, 2013
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000346352700069

Similar results(10)