1 resultado para Expert opinion
em Boston University Digital Common
Filtro por publicador
- Aberdeen University (1)
- Aberystwyth University Repository - Reino Unido (1)
- Aquatic Commons (3)
- Archive of European Integration (13)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (2)
- Aston University Research Archive (18)
- Avian Conservation and Ecology - Eletronic Cientific Hournal - Écologie et conservation des oiseaux: (1)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (1)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (2)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (2)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (39)
- Boston University Digital Common (1)
- Brock University, Canada (4)
- Brunel University (1)
- Cambridge University Engineering Department Publications Database (23)
- Carolina Law Scholarship Repository (1)
- CentAUR: Central Archive University of Reading - UK (65)
- Center for Jewish History Digital Collections (2)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (5)
- Cochin University of Science & Technology (CUSAT), India (2)
- Comissão Econômica para a América Latina e o Caribe (CEPAL) (77)
- CORA - Cork Open Research Archive - University College Cork - Ireland (1)
- Dalarna University College Electronic Archive (1)
- Deakin Research Online - Australia (92)
- DI-fusion - The institutional repository of Université Libre de Bruxelles (3)
- Digital Commons at Florida International University (1)
- Duke University (3)
- eResearch Archive - Queensland Department of Agriculture; Fisheries and Forestry (4)
- Gallica, Bibliotheque Numerique - Bibliothèque nationale de France (French National Library) (BnF), France (119)
- Greenwich Academic Literature Archive - UK (3)
- Helda - Digital Repository of University of Helsinki (6)
- Indian Institute of Science - Bangalore - Índia (19)
- Infoteca EMBRAPA (1)
- Instituto Politécnico de Viseu (1)
- Ministerio de Cultura, Spain (1)
- Nottingham eTheses (1)
- Plymouth Marine Science Electronic Archive (PlyMSEA) (3)
- Portal de Revistas Científicas Complutenses - Espanha (1)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (94)
- Queensland University of Technology - ePrints Archive (246)
- ReCiL - Repositório Científico Lusófona - Grupo Lusófona, Portugal (1)
- Repositório Científico da Universidade de Évora - Portugal (1)
- Repositório digital da Fundação Getúlio Vargas - FGV (3)
- Repositório Institucional da Universidade de Aveiro - Portugal (1)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (14)
- RUN (Repositório da Universidade Nova de Lisboa) - FCT (Faculdade de Cienecias e Technologia), Universidade Nova de Lisboa (UNL), Portugal (1)
- School of Medicine, Washington University, United States (2)
- Universidad Autónoma de Nuevo León, Mexico (1)
- Universidad de Alicante (2)
- Universidad del Rosario, Colombia (8)
- Universidad Politécnica de Madrid (3)
- Universidade Complutense de Madrid (2)
- Universidade de Lisboa - Repositório Aberto (1)
- Universidade Estadual Paulista "Júlio de Mesquita Filho" (UNESP) (1)
- Universitat de Girona, Spain (4)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (1)
- Université de Lausanne, Switzerland (8)
- Université de Montréal, Canada (18)
- University of Queensland eSpace - Australia (7)
- University of Southampton, United Kingdom (1)
- University of Washington (2)
- WestminsterResearch - UK (1)
- Worcester Research and Publications - Worcester Research and Publications - UK (1)
Resumo:
A new family of neural network architectures is presented. This family of architectures solves the problem of constructing and training minimal neural network classification expert systems by using switching theory. The primary insight that leads to the use of switching theory is that the problem of minimizing the number of rules and the number of IF statements (antecedents) per rule in a neural network expert system can be recast into the problem of minimizing the number of digital gates and the number of connections between digital gates in a Very Large Scale Integrated (VLSI) circuit. The rules that the neural network generates to perform a task are readily extractable from the network's weights and topology. Analysis and simulations on the Mushroom database illustrate the system's performance.