Logotipo del repositorio

Ponencias

URI permanente para esta colecciónhttp://10.0.96.45:4000/handle/11056/14724

Examinar

Examinando Ponencias por Materia "ANÁLISIS DE DATOS"

Seleccione resultados tecleando las primeras letras
Mostrando 1 - 2 de 2
  • No hay miniatura disponible
    Ítem
    Integer programming applied to rule based systems
    (Elsevier (Países Bajos), 2012) Ávila Herrera, Juan Félix
    Abstract. In this paper we show how to represent a set of logic propositions as an integer linear program and how to use its solution to determine the truth value of all the proposition given only a subset of their truth values. Thus a rule–based expert system might use this approach as inference engine. When we model an expert system knowledge base as an integer linear program, we can ask for what is a minimum set of premises needed in order to have an specific conclusion as true. Furthermore we can ask for what propositions become true once a subset of propositions are known to be true. Once the integer restriction is dismissed, we can ask for what conditions are necessary in order that a conclusion holds with certain probability. Thus we can have both a deterministic and stochastic model using practically the same paradigm.
  • No hay miniatura disponible
    Ítem
    Logical Analysis of Multi-Class Data
    (Institute of Electrical and Electronics Engineers (IEEE) (Estados Unidos), 2015) Avila-Herrera, Juan Félix; Subasi, Munevver Mine
    Abstract. Logical Analysis of Data (LAD) is a two-class learning algorithm which integrates principles of combinatorics, optimization, and the theory of Boolean functions. This paper proposes an algorithm based on mixed integer linear programming to extend the LAD methodology to solve multi-class classification problems, where One-vs-All (OvA) learning models are efficiently constructed to classify observations in predefined classes. The utility of the proposed approach is demonstrated through experiments on multi-class benchmark datasets.