Diaria: an integrated inference engine

• Autores: Juan Pedro Caraça-Valente Hernández , Asunción Gómez Pérez , Natalia Juristo, José Luis Morant Ramón
• Localización: Panel '92: actas, XVIII Conferencia Latinoamericana de Informática, 1992, págs. 248-254
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • To date all inference engines have been based on modus ponens which is, of course, a deductive inference rule, However, when making inference, human beings do not only use modus ponens or any other deductive inference rule, they also employ inductive, abductive and deductive inference rules, as required by they circumstances. In this paper, after having studied the different kinds of inference in AI: deductive, inductive, abductive and retroductive, we present a design of an inference engine which incorporates three of these kinds of inference and uses each of team when most appropiate, depending on the data, information and knowledge with which it is supplied at any time. Thus we have a true data-driven inference system.