Treffer: Application of the backpropagation algorithm to an information retrieval system
Title:
Application of the backpropagation algorithm to an information retrieval system
Authors:
Source:
Intelligent multimedia information retrieval systems and management (New York NY, October 11-12, 1994). :161-171
Publisher Information:
Paris: CID, 1994.
Publication Year:
1994
Physical Description:
print, 18 ref
Original Material:
INIST-CNRS
Subject Terms:
Documentation, Sciences exactes et technologie, Exact sciences and technology, Sciences et techniques communes, Sciences and techniques of general use, Sciences de l'information. Documentation, Information science. Documentation, Systèmes de recherche d'informations. Système de gestion documentaire et d'information, Information retrieval systems. Information and document management system, Systèmes de recherche d'information, Information retrieval systems, Sciences de l'information et de la communication, Information and communication sciences, Système de recherche documentaire. Système de gestion documentaire et d'information, Connexionnisme, Connectionism, Conexionismo, Informatique documentaire, Documentation data processing, Información documental, Algorithme, Algorithm, Algoritmo, Apprentissage, Learning, Aprendizaje, Auteur, Author, Autor, Conception système, System design, Concepción sistema, Modèle dynamique, Dynamic model, Modelo dinámico, Modèle théorique, Theoretical model, Modelo teórico, Noeud, Node, Nudo, Propagation, Propagación, Question documentaire, Query, Pregunta documental, Recherche développement, Research and development, Investigación desarrollo, Réseau neuronal, Neural network, Red neuronal, Système documentaire, Document retrieval system, Sistema recuperación documental, Terme indexation, Indexing term, Término indización, Expansion question, Query processing, Modèle connexionniste, Connectionist model, Organisation dynamique, Dynamic organization
Document Type:
Konferenz
Conference Paper
File Description:
text
Language:
English
Author Affiliations:
Univ. Bretagne occidentale, LERIA IUT/CGI, 56100 Lorient, France
Fac. sci. Limoges, lab. MSI, 87060 Limoges, France
Fac. sci. Limoges, lab. MSI, 87060 Limoges, France
Rights:
Copyright 1995 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Sciences of information and communication. Documentation
FRANCIS
FRANCIS
Accession Number:
edscal.3553688
Database:
PASCAL Archive
Weitere Informationen
This paper describes a dynamic Information Retrieval System (IRS) based on the neural appraoch. Our goal is to construct an IRS able to evolve in respect with the user's tendancy. We propose a network containing document, terms and author nodes where the links between these different nodes express the different relationships with may exist between them. A set of activation/propagation rules on which is based the information retrieval and the queries expansion algorithms are presented: At least, we propose a learning strategy inspired by the backpropagation algorithm to dynamically organize the information base.