FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1585425338> ?p ?o ?g. }

• W1585425338 abstract "This paper introduces the minimum entropy regularizer for learning from partial labels. This learning problem encompasses the semi-supervised setting, where a decision rule is to be learned from labeled and unlabeled examples. The minimum entropy regularizer applies to diagnosis models, i.e. models of the posterior probabilities of classes. It is shown to include other approaches to the semi-supervised problem as particular or limiting cases. A series of experiments illustrates that the proposed criterion provides solutions taking advantage of unlabeled examples when the latter convey information. Even when the data are sampled from the distribution class spanned by a generative model, the proposed approach improves over the estimated generative model when the number of features is of the order of sample size. The performances are definitely in favor of minimum entropy when the generative model is slightly misspecified. Finally, the robustness of the learning scheme is demonstrated: in situations where unlabeled examples do not convey information, minimum entropy returns a solution discarding unlabeled examples and performs as well as supervised learning. Cet article introduit le regularisateur a entropie minimum pour l'apprentissage d'etiquettes partielles. Ce probleme d'apprentissage incorpore le cadre non supervise, ou une regle de decision doit etre apprise a partir d'exemples etiquetes et non etiquetes. Le regularisateur a entropie minimum s'applique aux modeles de diagnostics, c'est-a-dire aux modeles des probabilites posterieures de classes. Nous montrons comment inclure d'autres approches comme un cas particulier ou limite du probleme semi-supervise. Une serie d'experiences montrent que le critere propose fournit des solutions utilisant les exemples non etiquetes lorsque ces dernieres sont instructives. Meme lorsque les donnees sont echantillonnees a partir de la classe de distribution balayee par un modele generatif, l'approche mentionnee ameliore le modele generatif estime lorsque le nombre de caracteristiques est de l'ordre de la taille de l'echantillon. Les performances avantagent certainement l'entropie minimum lorsque le modele generatif est legerement mal specifie. Finalement, la robustesse de ce cadre d'apprentissage est demontre : lors de situations ou les exemples non etiquetes n'apportent aucune information, l'entropie minimum retourne une solution rejetant les exemples non etiquetes et est aussi performante que l'apprentissage supervise." @default.
• W1585425338 created "2016-06-24" @default.
• W1585425338 creator A5021351429 @default.
• W1585425338 creator A5028826050 @default.
• W1585425338 date "2004-05-01" @default.
• W1585425338 modified "2023-09-27" @default.
• W1585425338 title "Learning from Partial Labels with Minimum Entropy" @default.
• W1585425338 cites W1537662695 @default.
• W1585425338 cites W1574877594 @default.
• W1585425338 cites W1988520084 @default.
• W1585425338 cites W2037603696 @default.
• W1585425338 cites W2059279601 @default.
• W1585425338 cites W2077096052 @default.
• W1585425338 cites W2097089247 @default.
• W1585425338 cites W2107968230 @default.
• W1585425338 cites W2129476886 @default.
• W1585425338 cites W2130037226 @default.
• W1585425338 cites W2131775048 @default.
• W1585425338 cites W2144372981 @default.
• W1585425338 cites W2148603752 @default.
• W1585425338 cites W2149950545 @default.
• W1585425338 cites W2152553986 @default.
• W1585425338 cites W2165794341 @default.
• W1585425338 cites W2974222084 @default.
• W1585425338 cites W38936090 @default.
• W1585425338 hasPublicationYear "2004" @default.
• W1585425338 type Work @default.
• W1585425338 sameAs 1585425338 @default.
• W1585425338 citedByCount "9" @default.
• W1585425338 countsByYear W15854253382012 @default.
• W1585425338 countsByYear W15854253382015 @default.
• W1585425338 countsByYear W15854253382018 @default.
• W1585425338 countsByYear W15854253382019 @default.
• W1585425338 countsByYear W15854253382021 @default.
• W1585425338 crossrefType "posted-content" @default.
• W1585425338 hasAuthorship W1585425338A5021351429 @default.
• W1585425338 hasAuthorship W1585425338A5028826050 @default.
• W1585425338 hasConcept C106301342 @default.
• W1585425338 hasConcept C119857082 @default.
• W1585425338 hasConcept C121332964 @default.
• W1585425338 hasConcept C127413603 @default.
• W1585425338 hasConcept C154945302 @default.
• W1585425338 hasConcept C167966045 @default.
• W1585425338 hasConcept C188198153 @default.
• W1585425338 hasConcept C33923547 @default.
• W1585425338 hasConcept C39890363 @default.
• W1585425338 hasConcept C41008148 @default.
• W1585425338 hasConcept C62520636 @default.
• W1585425338 hasConcept C78519656 @default.
• W1585425338 hasConceptScore W1585425338C106301342 @default.
• W1585425338 hasConceptScore W1585425338C119857082 @default.
• W1585425338 hasConceptScore W1585425338C121332964 @default.
• W1585425338 hasConceptScore W1585425338C127413603 @default.
• W1585425338 hasConceptScore W1585425338C154945302 @default.
• W1585425338 hasConceptScore W1585425338C167966045 @default.
• W1585425338 hasConceptScore W1585425338C188198153 @default.
• W1585425338 hasConceptScore W1585425338C33923547 @default.
• W1585425338 hasConceptScore W1585425338C39890363 @default.
• W1585425338 hasConceptScore W1585425338C41008148 @default.
• W1585425338 hasConceptScore W1585425338C62520636 @default.
• W1585425338 hasConceptScore W1585425338C78519656 @default.
• W1585425338 hasLocation W15854253381 @default.
• W1585425338 hasOpenAccess W1585425338 @default.
• W1585425338 hasPrimaryLocation W15854253381 @default.
• W1585425338 hasRelatedWork W1550508914 @default.
• W1585425338 hasRelatedWork W1974596106 @default.
• W1585425338 hasRelatedWork W2024328138 @default.
• W1585425338 hasRelatedWork W2111478152 @default.
• W1585425338 hasRelatedWork W2132509897 @default.
• W1585425338 hasRelatedWork W2137917285 @default.
• W1585425338 hasRelatedWork W2142863987 @default.
• W1585425338 hasRelatedWork W2144372981 @default.
• W1585425338 hasRelatedWork W2146111596 @default.
• W1585425338 hasRelatedWork W2153603270 @default.
• W1585425338 hasRelatedWork W2158681777 @default.
• W1585425338 hasRelatedWork W2285223868 @default.
• W1585425338 hasRelatedWork W2338068721 @default.
• W1585425338 hasRelatedWork W2733555913 @default.
• W1585425338 hasRelatedWork W3021036236 @default.
• W1585425338 hasRelatedWork W3120740533 @default.
• W1585425338 hasRelatedWork W3122936144 @default.
• W1585425338 hasRelatedWork W3123737980 @default.
• W1585425338 hasRelatedWork W3124320086 @default.
• W1585425338 hasRelatedWork W590635534 @default.
• W1585425338 isParatext "false" @default.
• W1585425338 isRetracted "false" @default.
• W1585425338 magId "1585425338" @default.
• W1585425338 workType "article" @default.