Mostra el registre d'ítem simple

dc.contributor.authorBuchaca Prats, David
dc.contributor.authorRomero Merino, Enrique
dc.contributor.authorMazzanti Castrillejo, Fernando Pablo
dc.contributor.authorDelgado Pin, Jordi
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Física i Enginyeria Nuclear
dc.date.accessioned2015-03-09T12:28:53Z
dc.date.available2015-03-09T12:28:53Z
dc.date.created2014
dc.date.issued2014
dc.identifier.citationBuchaca, D. [et al.]. Stopping criteria in contrastive divergence: Alternatives to the reconstruction error. A: International Conference on Learning Representations. "International Conference on Learning Representations 2014: workshop proceedings". Banff: 2014.
dc.identifier.urihttp://hdl.handle.net/2117/26625
dc.description.abstractRestricted Boltzmann Machines (RBMs) are general unsupervised learning devices to ascertain generative models of data distributions. RBMs are often trained using the Contrastive Divergence learning algorithm (CD), an approximation to the gradient of the data log-likelihood. A simple reconstruction error is often used to decide whether the approximation provided by the CD algorithm is good enough, though several authors (Schulz et al., 2010; Fischer & Igel, 2010) have raised doubts concerning the feasibility of this procedure. However, not many alternatives to the reconstruction error have been used in the literature. In this manuscript we investigate simple alternatives to the reconstruction error in order to detect as soon as possible the decrease in the log-likelihood during learning.
dc.format.extent8 p.
dc.language.isoeng
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subject.lcshMachine learning
dc.subject.lcshComputer algorithms
dc.subject.otherRestricted Boltzmann Machines
dc.subject.otherRBMs: Contrastive divergence learning algorithm
dc.titleStopping criteria in contrastive divergence: Alternatives to the reconstruction error
dc.typeConference report
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacAlgorismes computacionals
dc.contributor.groupUniversitat Politècnica de Catalunya. SOCO - Soft Computing
dc.contributor.groupUniversitat Politècnica de Catalunya. SIMCON - First-principles approaches to condensed matter physics: quantum effects and complexity
dc.contributor.groupUniversitat Politècnica de Catalunya. LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://sites.google.com/site/representationlearning2014/workshop-proceedings
dc.rights.accessOpen Access
local.identifier.drac15451088
dc.description.versionPostprint (published version)
local.citation.authorBuchaca, D.; Romero, E.; Mazzanti, F.; Delgado, J.
local.citation.contributorInternational Conference on Learning Representations
local.citation.pubplaceBanff
local.citation.publicationNameInternational Conference on Learning Representations 2014: workshop proceedings


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple