Mostra el registre d'ítem simple
Neighborhood-based stopping criterion for contrastive divergence
dc.contributor.author | Romero Merino, Enrique |
dc.contributor.author | Mazzanti Castrillejo, Fernando Pablo |
dc.contributor.author | Delgado Pin, Jordi |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Física |
dc.date.accessioned | 2018-12-13T08:22:27Z |
dc.date.available | 2018-12-13T08:22:27Z |
dc.date.issued | 2018-07 |
dc.identifier.citation | Romero, E., Mazzanti, F., Delgado, J. Neighborhood-based stopping criterion for contrastive divergence. "IEEE transactions on neural networks and learning systems", Juliol 2018, vol. 29, núm. 7, p. 2695-2704. |
dc.identifier.issn | 2162-237X |
dc.identifier.uri | http://hdl.handle.net/2117/125738 |
dc.description.abstract | Restricted Boltzmann Machines (RBMs) are general unsupervised learning devices to ascertain generative models of data distributions. RBMs are often trained using the Contrastive Divergence (CD) learning algorithm, an approximation to the gradient of the data log-likelihood (logL). A simple reconstruction error is often used as a stopping criterion for CD, although several authors have raised doubts concerning the feasibility of this procedure. In many cases, the evolution curve of the reconstruction error is monotonic, while the logL is not, thus indicating that the former is not a good estimator of the optimal stopping point for learning. However, not many alternatives to the reconstruction error have been discussed in the literature. An estimation of the logL of the training data based on annealed importance sampling is feasible but computationally very expensive. In this manuscript, we present a simple and cheap alternative, based on the inclusion of information contained in neighboring states to the training set, as a stopping criterion for CD learning. |
dc.format.extent | 10 p. |
dc.language.iso | eng |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic |
dc.subject.lcsh | Machine learning |
dc.subject.lcsh | Neural networks (Computer science) |
dc.subject.other | Recurrent neural networks |
dc.subject.other | Restricted Boltzmann machines |
dc.subject.other | Unsupervised learning |
dc.title | Neighborhood-based stopping criterion for contrastive divergence |
dc.type | Article |
dc.subject.lemac | Aprenentatge automàtic |
dc.subject.lemac | Xarxes neuronals (Informàtica) |
dc.contributor.group | Universitat Politècnica de Catalunya. SIMCON - First-principles approaches to condensed matter physics: quantum effects and complexity |
dc.contributor.group | Universitat Politècnica de Catalunya. LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge |
dc.identifier.doi | 10.1109/TNNLS.2017.2697455 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | https://ieeexplore.ieee.org/document/7930408 |
dc.rights.access | Open Access |
local.identifier.drac | 23537879 |
dc.description.version | Postprint (author's final draft) |
dc.relation.projectid | info:eu-repo/grantAgreement/MINECO/1PE/TIN2016-79576-R |
dc.relation.projectid | info:eu-repo/grantAgreement/MINECO//FIS2014-56257-C2-1-P/ES/MATERIA CUÁNTICA ULTRAFRIA/ |
dc.relation.projectid | info:eu-repo/grantAgreement/AGAUR/V PRI/2014 SGR 890 |
dc.relation.projectid | info:eu-repo/grantAgreement/MINECO//TIN2014-57226-P/ES/APRENDIZAJE COMPUTACIONAL Y COMUNICACION/ |
local.citation.author | Romero, E.; Mazzanti, F.; Delgado, J. |
local.citation.publicationName | IEEE transactions on neural networks and learning systems |
local.citation.volume | 29 |
local.citation.number | 7 |
local.citation.startingPage | 2695 |
local.citation.endingPage | 2704 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Articles de revista [134]
-
Articles de revista [2.208]
-
Articles de revista [1.049]
-
Articles de revista [383]