1 resultado para Trace Rule
em University of Queensland eSpace - Australia
Filtro por publicador
- Aberystwyth University Repository - Reino Unido (8)
- Acceda, el repositorio institucional de la Universidad de Las Palmas de Gran Canaria. España (4)
- Adam Mickiewicz University Repository (2)
- AMS Tesi di Dottorato - Alm@DL - Università di Bologna (3)
- Applied Math and Science Education Repository - Washington - USA (1)
- Aquatic Commons (14)
- ArchiMeD - Elektronische Publikationen der Universität Mainz - Alemanha (8)
- Archive of European Integration (3)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (14)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (18)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (17)
- Biblioteca Digital de la Universidad Católica Argentina (2)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (86)
- Boston College Law School, Boston College (BC), United States (1)
- Boston University Digital Common (3)
- Brock University, Canada (6)
- Bucknell University Digital Commons - Pensilvania - USA (1)
- CaltechTHESIS (1)
- Cambridge University Engineering Department Publications Database (16)
- CentAUR: Central Archive University of Reading - UK (86)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (96)
- Cochin University of Science & Technology (CUSAT), India (25)
- Collection Of Biostatistics Research Archive (2)
- Comissão Econômica para a América Latina e o Caribe (CEPAL) (4)
- CORA - Cork Open Research Archive - University College Cork - Ireland (1)
- Dalarna University College Electronic Archive (5)
- Deakin Research Online - Australia (103)
- Department of Computer Science E-Repository - King's College London, Strand, London (1)
- DI-fusion - The institutional repository of Université Libre de Bruxelles (4)
- DigitalCommons - The University of Maine Research (3)
- DigitalCommons@The Texas Medical Center (5)
- DigitalCommons@University of Nebraska - Lincoln (1)
- Digitale Sammlungen - Goethe-Universität Frankfurt am Main (2)
- Diposit Digital de la UB - Universidade de Barcelona (1)
- Duke University (2)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (2)
- Gallica, Bibliotheque Numerique - Bibliothèque nationale de France (French National Library) (BnF), France (2)
- Greenwich Academic Literature Archive - UK (2)
- Helda - Digital Repository of University of Helsinki (4)
- Indian Institute of Science - Bangalore - Índia (36)
- Infoteca EMBRAPA (1)
- Instituto Politécnico do Porto, Portugal (3)
- Lume - Repositório Digital da Universidade Federal do Rio Grande do Sul (1)
- Massachusetts Institute of Technology (2)
- Plymouth Marine Science Electronic Archive (PlyMSEA) (30)
- Portal de Revistas Científicas Complutenses - Espanha (1)
- Publishing Network for Geoscientific & Environmental Data (90)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (86)
- Queensland University of Technology - ePrints Archive (88)
- ReCiL - Repositório Científico Lusófona - Grupo Lusófona, Portugal (1)
- Repositório Científico do Instituto Politécnico de Lisboa - Portugal (1)
- Repositório digital da Fundação Getúlio Vargas - FGV (21)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (46)
- RUN (Repositório da Universidade Nova de Lisboa) - FCT (Faculdade de Cienecias e Technologia), Universidade Nova de Lisboa (UNL), Portugal (2)
- SAPIENTIA - Universidade do Algarve - Portugal (4)
- School of Medicine, Washington University, United States (1)
- Universidad Autónoma de Nuevo León, Mexico (1)
- Universidad del Rosario, Colombia (1)
- Universidade Federal do Pará (1)
- Universidade Federal do Rio Grande do Norte (UFRN) (1)
- Universitat de Girona, Spain (1)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (1)
- Université de Lausanne, Switzerland (2)
- Université de Montréal, Canada (10)
- University of Connecticut - USA (6)
- University of Queensland eSpace - Australia (1)
- University of Southampton, United Kingdom (1)
- University of Washington (1)
Resumo:
A biologically realizable, unsupervised learning rule is described for the online extraction of object features, suitable for solving a range of object recognition tasks. Alterations to the basic learning rule are proposed which allow the rule to better suit the parameters of a given input space. One negative consequence of such modifications is the potential for learning instability. The criteria for such instability are modeled using digital filtering techniques and predicted regions of stability and instability tested. The result is a family of learning rules which can be tailored to the specific environment, improving both convergence times and accuracy over the standard learning rule, while simultaneously insuring learning stability.