Exploració per autor "Delgado Calvo-Flores, Miguel"

Ara es mostren els items 1-6 de 6

    • A survey of methods to evaluate quantified sentences 

      Delgado Calvo-Flores, Miguel; Sánchez Fernández, Daniel; Serrano Chica, José María; Vila Miranda, María Amparo (Universitat Politècnica de Catalunya. Secció de Matemàtiques i Informàtica, 2000)
      Article
      Accés obert
      The evaluation of quantified sentences is used to solve several problems. Most of the methods proposed in the literature are not satisfactory because they do not verify some intuitive properties. In this paper we propose ...

    • Evolutionaty training for dynamical recurrent neural networks: an application in finantial time series prediction 

      Delgado Calvo-Flores, Miguel; Pegalajar Jiménez, Mª Carmen; Pegalajar Cuéllar, Manuel (Universitat Politècnica de Catalunya. Secció de Matemàtiques i Informàtica, 2006)
      Article
      Accés obert
      Theoretical and experimental studies have shown that traditional training algorithms for Dynamical Recurrent Neural Networks may suffer of local optima solutions, due to the error propagation across the recurrence. In the ...

    • Fuzzy numbers, definitions and properties 

      Delgado Calvo-Flores, Miguel; Verdegay, José Luis; Vila Miranda, María Amparo (Universitat Politècnica de Catalunya. Secció de Matemàtiques i Informàtica, 1994)
      Article
      Accés obert
      Two different definitions of a Fuzzy number may be found in the literature. Both fulfill Goguen's Fuzzification Principle but are different in nature because of their different starting points. The first one was introduced ...

    • Max-Min fuzzy neural networks for solving relational equations 

      Blanco Morón, Armando; Delgado Calvo-Flores, Miguel; Requena Ramos, Ignacio (Universitat Politècnica de Catalunya. Secció de Matemàtiques i Informàtica, 1994)
      Article
      Accés obert
      The Relational Equations approach is one of the most usual ones for describing (Fuzzy) Systems and in most cases, it is the final expression for other descriptions. This is why the identification of Relational Equations ...

    • Neural methods for obtaining fuzzy rules 

      Benítez Sánchez, José Manuel; Blanco Morón, Armando; Delgado Calvo-Flores, Miguel; Requena Ramos, Ignacio (Universitat Politècnica de Catalunya. Secció de Matemàtiques i Informàtica, 1996)
      Article
      Accés obert
      In previous papers, we presented an empirical methodology based on Neural Networks for obtaining fuzzy rules which allow a system to be described, using a set of examples with the corresponding inputs and outputs. Now ...

    • New aspects on extraction of fuzzy rules using neural networks 

      Benítez Sánchez, José Manuel; Blanco Morón, Armando; Delgado Calvo-Flores, Miguel; Requena Ramos, Ignacio (Universitat Politècnica de Catalunya. Secció de Matemàtiques i Informàtica, 1998)
      Article
      Accés obert
      In previous works, we have presented two methodologies to obtain fuzzy rules in order to describe the behaviour of a system. We have used Artificial Neural Netorks (ANN) with the {\it Backpropagation} algorithm, and a set ...