1 resultado para Hilbert, Transformada de
em Aston University Research Archive
Filtro por publicador
- KUPS-Datenbank - Universität zu Köln - Kölner UniversitätsPublikationsServer (1)
- Aberystwyth University Repository - Reino Unido (1)
- Academic Archive On-line (Stockholm University; Sweden) (2)
- Academic Research Repository at Institute of Developing Economies (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 (3)
- AMS Tesi di Laurea - Alm@DL - Università di Bologna (26)
- Andina Digital - Repositorio UASB-Digital - Universidade Andina Simón Bolívar (3)
- ArchiMeD - Elektronische Publikationen der Universität Mainz - Alemanha (14)
- Archivo Digital para la Docencia y la Investigación - Repositorio Institucional de la Universidad del País Vasco (11)
- Aston University Research Archive (1)
- Biblioteca de Teses e Dissertações da USP (4)
- Biblioteca Digital da Câmara dos Deputados (1)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (11)
- Biblioteca Digital da Produção Intelectual da Universidade de São Paulo (BDPI/USP) (6)
- Biblioteca Digital de la Universidad Católica Argentina (1)
- Biblioteca Digital de Teses e Dissertações Eletrônicas da UERJ (24)
- Bibloteca do Senado Federal do Brasil (1)
- BORIS: Bern Open Repository and Information System - Berna - Suiça (10)
- Boston University Digital Common (1)
- Bucknell University Digital Commons - Pensilvania - USA (3)
- Bulgarian Digital Mathematics Library at IMI-BAS (12)
- CaltechTHESIS (8)
- Cámara de Comercio de Bogotá, Colombia (1)
- Cambridge University Engineering Department Publications Database (8)
- CentAUR: Central Archive University of Reading - UK (27)
- Chinese Academy of Sciences Institutional Repositories Grid Portal (14)
- Cochin University of Science & Technology (CUSAT), India (3)
- Comissão Econômica para a América Latina e o Caribe (CEPAL) (25)
- CORA - Cork Open Research Archive - University College Cork - Ireland (1)
- Dalarna University College Electronic Archive (1)
- Deakin Research Online - Australia (6)
- Department of Computer Science E-Repository - King's College London, Strand, London (2)
- Digital Commons - Michigan Tech (1)
- DigitalCommons@The Texas Medical Center (2)
- Digitale Sammlungen - Goethe-Universität Frankfurt am Main (1)
- Duke University (1)
- FAUBA DIGITAL: Repositorio institucional científico y académico de la Facultad de Agronomia de la Universidad de Buenos Aires (1)
- Funes: Repositorio digital de documentos en Educación Matemática - Colombia (6)
- Helda - Digital Repository of University of Helsinki (4)
- Indian Institute of Science - Bangalore - Índia (60)
- Infoteca EMBRAPA (4)
- INSTITUTO DE PESQUISAS ENERGÉTICAS E NUCLEARES (IPEN) - Repositório Digital da Produção Técnico Científica - BibliotecaTerezine Arantes Ferra (1)
- Instituto Politécnico de Leiria (1)
- Instituto Politécnico do Porto, Portugal (7)
- Livre Saber - Repositório Digital de Materiais Didáticos - SEaD-UFSCar (1)
- Lume - Repositório Digital da Universidade Federal do Rio Grande do Sul (41)
- Massachusetts Institute of Technology (2)
- Memoria Académica - FaHCE, UNLP - Argentina (4)
- Ministerio de Cultura, Spain (19)
- QSpace: Queen's University - Canada (1)
- QUB Research Portal - Research Directory and Institutional Repository for Queen's University Belfast (37)
- Queensland University of Technology - ePrints Archive (24)
- RDBU - Repositório Digital da Biblioteca da Unisinos (3)
- ReCiL - Repositório Científico Lusófona - Grupo Lusófona, Portugal (2)
- Repositório Científico da Universidade de Évora - Portugal (1)
- Repositório Científico do Instituto Politécnico de Lisboa - Portugal (7)
- Repositório digital da Fundação Getúlio Vargas - FGV (4)
- Repositório Digital da UNIVERSIDADE DA MADEIRA - Portugal (4)
- Repositório Digital da Universidade Municipal de São Caetano do Sul - USCS (1)
- REPOSITORIO DIGITAL IMARPE - INSTITUTO DEL MAR DEL PERÚ, Peru (1)
- Repositorio Institucional da UFLA (RIUFLA) (2)
- Repositório Institucional da Universidade de Aveiro - Portugal (10)
- Repositório Institucional da Universidade de Brasília (1)
- Repositório Institucional da Universidade Estadual de São Paulo - UNESP (3)
- Repositório Institucional da Universidade Tecnológica Federal do Paraná (RIUT) (1)
- Repositorio Institucional de la Universidad de El Salvador (1)
- Repositorio Institucional de la Universidad Nacional Agraria (1)
- Repositório Institucional UNESP - Universidade Estadual Paulista "Julio de Mesquita Filho" (264)
- Repositorio Institucional Universidad EAFIT - Medelin - Colombia (2)
- 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 (2)
- Universidad Autónoma de Nuevo León, Mexico (3)
- Universidad del Rosario, Colombia (3)
- Universidad Politécnica de Madrid (4)
- Universidade Complutense de Madrid (3)
- Universidade de Lisboa - Repositório Aberto (5)
- Universidade Federal de Uberlândia (1)
- Universidade Federal do Pará (35)
- Universidade Federal do Rio Grande do Norte (UFRN) (116)
- Universitat de Girona, Spain (9)
- Universitätsbibliothek Kassel, Universität Kassel, Germany (3)
- Université de Lausanne, Switzerland (2)
- Université de Montréal, Canada (11)
- University of Michigan (7)
- University of Queensland eSpace - Australia (2)
Resumo:
This thesis describes a novel connectionist machine utilizing induction by a Hilbert hypercube representation. This representation offers a number of distinct advantages which are described. We construct a theoretical and practical learning machine which lies in an area of overlap between three disciplines - neural nets, machine learning and knowledge acquisition - hence it is refered to as a "coalesced" machine. To this unifying aspect is added the various advantages of its orthogonal lattice structure as against less structured nets. We discuss the case for such a fundamental and low level empirical learning tool and the assumptions behind the machine are clearly outlined. Our theory of an orthogonal lattice structure the Hilbert hypercube of an n-dimensional space using a complemented distributed lattice as a basis for supervised learning is derived from first principles on clearly laid out scientific principles. The resulting "subhypercube theory" was implemented in a development machine which was then used to test the theoretical predictions again under strict scientific guidelines. The scope, advantages and limitations of this machine were tested in a series of experiments. Novel and seminal properties of the machine include: the "metrical", deterministic and global nature of its search; complete convergence invariably producing minimum polynomial solutions for both disjuncts and conjuncts even with moderate levels of noise present; a learning engine which is mathematically analysable in depth based upon the "complexity range" of the function concerned; a strong bias towards the simplest possible globally (rather than locally) derived "balanced" explanation of the data; the ability to cope with variables in the network; and new ways of reducing the exponential explosion. Performance issues were addressed and comparative studies with other learning machines indicates that our novel approach has definite value and should be further researched.