1 resultado para Shannon entropy
em Massachusetts Institute of Technology
Filtro por publicador
- Repository Napier (1)
- Academic Archive On-line (Karlstad University; Sweden) (1)
- Acceda, el repositorio institucional de la Universidad de Las Palmas de Gran Canaria. España (1)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (1)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (5)
- Aquatic Commons (14)
- Archive of European Integration (1)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (6)
- Aston University Research Archive (30)
- Biblioteca Digital - Universidad Icesi - Colombia (1)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (16)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (12)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (16)
- Bibloteca do Senado Federal do Brasil (7)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (11)
- Boston University Digital Common (1)
- Brock University, Canada (5)
- Bulgarian Digital Mathematics Library at IMI-BAS (2)
- CaltechTHESIS (17)
- Cambridge University Engineering Department Publications Database (41)
- CentAUR: Central Archive University of Reading - UK (13)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (38)
- Cochin University of Science & Technology (CUSAT), India (9)
- CORA - Cork Open Research Archive - University College Cork - Ireland (1)
- Corvinus Research Archive - The institutional repository for the Corvinus University of Budapest (1)
- Deakin Research Online - Australia (29)
- Department of Computer Science E-Repository - King's College London, Strand, London (1)
- Digital Archives@Colby (1)
- Digital Commons at Florida International University (2)
- Diposit Digital de la UB - Universidade de Barcelona (7)
- DRUM (Digital Repository at the University of Maryland) (1)
- Duke University (1)
- Düsseldorfer Dokumenten- und Publikationsservice (1)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (3)
- FUNDAJ - Fundação Joaquim Nabuco (3)
- Greenwich Academic Literature Archive - UK (1)
- Helda - Digital Repository of University of Helsinki (9)
- Indian Institute of Science - Bangalore - Índia (264)
- Instituto Politécnico do Porto, Portugal (3)
- Instituto Superior de Psicologia Aplicada - Lisboa (1)
- Massachusetts Institute of Technology (1)
- National Center for Biotechnology Information - NCBI (5)
- Publishing Network for Geoscientific & Environmental Data (13)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (27)
- Queensland University of Technology - ePrints Archive (222)
- Repositório digital da Fundação Getúlio Vargas - FGV (1)
- Repositório Digital da Universidade Municipal de São Caetano do Sul - USCS (1)
- Repositório Institucional da Universidade de Aveiro - Portugal (2)
- Repositorio Institucional de la Universidad Nacional Agraria (10)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (39)
- SAPIENTIA - Universidade do Algarve - Portugal (2)
- Universidad de Alicante (3)
- Universidad Politécnica de Madrid (12)
- Universidade Complutense de Madrid (4)
- Universidade Federal do Pará (1)
- Universidade Federal do Rio Grande do Norte (UFRN) (3)
- Universitat de Girona, Spain (2)
- Université de Lausanne, Switzerland (1)
- University of Canberra Research Repository - Australia (1)
- University of Michigan (15)
- University of Queensland eSpace - Australia (12)
- University of Southampton, United Kingdom (2)
Resumo:
We present a general framework for discriminative estimation based on the maximum entropy principle and its extensions. All calculations involve distributions over structures and/or parameters rather than specific settings and reduce to relative entropy projections. This holds even when the data is not separable within the chosen parametric class, in the context of anomaly detection rather than classification, or when the labels in the training set are uncertain or incomplete. Support vector machines are naturally subsumed under this class and we provide several extensions. We are also able to estimate exactly and efficiently discriminative distributions over tree structures of class-conditional models within this framework. Preliminary experimental results are indicative of the potential in these techniques.