FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1543752008> ?p ?o ?g. }

• W1543752008 endingPage "216" @default.
• W1543752008 startingPage "209" @default.
• W1543752008 abstract "The maximum entropy (MaxEnt) framework has been studied extensively in the supervised setting. Here, the goal is to find a distribution p that maximizes an entropy function while enforcing data constraints so that the expected values of some (pre-defined) features with respect to p match their empirical counterparts approximately. Using different entropy measures, different model spaces for p, and different approximation criteria for the data constraints, yields a family of discriminative supervised learning methods (e.g., logistic regression, conditional random fields, least squares and boosting) (Dudik & Schapire, 2006; Friedlander & Gupta, 2006; Altun & Smola, 2006). This framework is known as the generalized maximum entropy framework.Semi-supervised learning (SSL) is a promising field that has increasingly attracted attention in the last decade. SSL algorithms utilize unlabeled data along with labeled data so as to increase the accuracy and robustness of inference algorithms. However, most SSL algorithms to date have had trade-offs, e.g., in terms of scalability or applicability to multi-categorical data. In this thesis, we extend the generalized MaxEnt framework to develop a family of novel SSL algorithms using two different approaches: (1) Introducing Similarity Constraints We incorporate unlabeled data via modifications to the primal MaxEnt objective in terms of additional potential functions. A potential function stands for a closed proper convex function that can take the form of a constraint and/or a penalty representing our structural assumptions on the data geometry. Specifically, we impose similarity constraints as additional penalties based on the semi-supervised smoothness assumption , i.e., we restrict the MaxEnt problem such that similar samples have similar model outputs. The motivation is reminiscent of that of Laplacian SVM (Sindhwani et al., 2005) and manifold transductive neural networks (Karlen et al., 2008), however, instead of regularizing the loss function in the dual we integrate our constraints directly to the primal MaxEnt problem which has a more straight-forward and natural interpretation. (2) Augmenting Constraints on Model Features We incorporate unlabeled data to enhance the moment matching constraints of the generalized MaxEnt problem in the primal. We improve the estimates of the model and empirical expectations of the feature functions using our assumptions on the data geometry.In particular, we derive the semi-supervised formulations for three specific instances of the generalized MaxEnt framework on conditional distributions, namely logistic regression and kernel logistic regression for multi-class problems, and conditional random fields for structured output prediction problems. A thorough empirical evaluation on standard data sets that are widely used in the literature demonstrates the validity and competitiveness of the proposed algorithms. In addition to these benchmark data sets, we apply our approach to two real-life problems, vision based robot grasping, and remote sensing image classification where the scarcity of the labeled training samples is the main bottleneck in the learning process. For the particular case of grasp learning, we also propose a combination of semi-supervised learning and active learning, another sub-field of machine learning that is focused on the scarcity of labeled samples, when the problem setup is suitable for incremental labeling.To conclude, the novel SSL algorithms proposed in this thesis have numerous advantages over the existing semi-supervised algorithms as they yield convex, scalable, inherently multi-class loss functions that can be kernelized naturally." @default.
• W1543752008 created "2016-06-24" @default.
• W1543752008 creator A5001226970 @default.
• W1543752008 creator A5090371841 @default.
• W1543752008 date "2010-01-01" @default.
• W1543752008 modified "2023-09-22" @default.
• W1543752008 title "Semi-supervised learning via generalized maximum entropy" @default.
• W1543752008 cites W1479807131 @default.
• W1543752008 cites W1489844845 @default.
• W1543752008 cites W1497443639 @default.
• W1543752008 cites W1506806321 @default.
• W1543752008 cites W1509803206 @default.
• W1543752008 cites W1513874326 @default.
• W1543752008 cites W1529196404 @default.
• W1543752008 cites W1546961578 @default.
• W1543752008 cites W1548714966 @default.
• W1543752008 cites W1551944942 @default.
• W1543752008 cites W1560724230 @default.
• W1543752008 cites W1574862351 @default.
• W1543752008 cites W1574877594 @default.
• W1543752008 cites W1579838312 @default.
• W1543752008 cites W1585529040 @default.
• W1543752008 cites W1630959083 @default.
• W1543752008 cites W1640100566 @default.
• W1543752008 cites W1663973292 @default.
• W1543752008 cites W1787054552 @default.
• W1543752008 cites W1820657498 @default.
• W1543752008 cites W1881594620 @default.
• W1543752008 cites W1979945719 @default.
• W1543752008 cites W1982032418 @default.
• W1543752008 cites W1996903695 @default.
• W1543752008 cites W2002806284 @default.
• W1543752008 cites W2005073772 @default.
• W1543752008 cites W2014566476 @default.
• W1543752008 cites W2031823405 @default.
• W1543752008 cites W2032558547 @default.
• W1543752008 cites W2038721957 @default.
• W1543752008 cites W2041376653 @default.
• W1543752008 cites W2074045464 @default.
• W1543752008 cites W2077261816 @default.
• W1543752008 cites W2095758845 @default.
• W1543752008 cites W2096175520 @default.
• W1543752008 cites W2101902009 @default.
• W1543752008 cites W2105180921 @default.
• W1543752008 cites W2105842272 @default.
• W1543752008 cites W2107640784 @default.
• W1543752008 cites W2107968230 @default.
• W1543752008 cites W2112796928 @default.
• W1543752008 cites W2113592823 @default.
• W1543752008 cites W2115511080 @default.
• W1543752008 cites W2115933183 @default.
• W1543752008 cites W2116556696 @default.
• W1543752008 cites W2117729721 @default.
• W1543752008 cites W2122457239 @default.
• W1543752008 cites W2125838338 @default.
• W1543752008 cites W2127230571 @default.
• W1543752008 cites W2127816222 @default.
• W1543752008 cites W2132146097 @default.
• W1543752008 cites W2134134392 @default.
• W1543752008 cites W2135484641 @default.
• W1543752008 cites W2136504847 @default.
• W1543752008 cites W2137116439 @default.
• W1543752008 cites W2137515156 @default.
• W1543752008 cites W2141416357 @default.
• W1543752008 cites W2142114717 @default.
• W1543752008 cites W2142165428 @default.
• W1543752008 cites W2145494108 @default.
• W1543752008 cites W2147880316 @default.
• W1543752008 cites W2148029428 @default.
• W1543752008 cites W2148603752 @default.
• W1543752008 cites W2149950545 @default.
• W1543752008 cites W2150969560 @default.
• W1543752008 cites W2151689911 @default.
• W1543752008 cites W2151716017 @default.
• W1543752008 cites W2153838241 @default.
• W1543752008 cites W2154462399 @default.
• W1543752008 cites W2157094900 @default.
• W1543752008 cites W2160842254 @default.
• W1543752008 cites W2163306339 @default.
• W1543752008 cites W2165874743 @default.
• W1543752008 cites W2169241897 @default.
• W1543752008 cites W2169336678 @default.
• W1543752008 cites W2282336968 @default.
• W1543752008 cites W2312997001 @default.
• W1543752008 cites W2331182131 @default.
• W1543752008 cites W2469994344 @default.
• W1543752008 cites W2561879720 @default.
• W1543752008 cites W2903158431 @default.
• W1543752008 cites W3145128584 @default.
• W1543752008 cites W3151142710 @default.
• W1543752008 cites W345014192 @default.
• W1543752008 cites W36398315 @default.
• W1543752008 cites W92894758 @default.
• W1543752008 cites W1542491098 @default.
• W1543752008 cites W2161391345 @default.
• W1543752008 hasPublicationYear "2010" @default.
• W1543752008 type Work @default.
• W1543752008 sameAs 1543752008 @default.

• next