A technique is described in this chapter that makes it possible to extract the knowledge held by previously trained artificial neural networks. This makes it possible for them to be used in a number of areas (such as medicine) where it is necessary to know how they work, as well as having a network that functions. This chapter explains how to carry out this process to extract knowledge, defined as rules. Special emphasis is placed on extracting knowledge from recurrent neural networks, in particular when applied in predicting time series.
Complete Chapter List
Ana B. Porto, Alejandro Pazos
Eduardo D. Martin, Alfonso Araque
Paulo Cortez, Miguel Rocha, José Neves
Julián Dorado, Nieves Pedreira, Mónica Miguelez
Daniel Manrique, Juan Rios, Alfonso Rodriguez-Paton
Daniel Rivero, Miguel Varela, Javier Pereira
Marcos G. Pose, Alberto C. Carollo, José M.A. Garda, Mari P. Gomez-Carracedo
Juan R. Rabunal, Juan Puertas
Belén Gonzalez, M. Isabel Martinez, Diego Carro
Robert Perkins, Anthony Brabazon
Alfonso Iglesias, Bernardino Arcay, José M. Cotos
Kun-Chang Lee, Tae-Young Paik
Tarun Bhaskar, Narasimha Kamath B.
Alejandra Rodriguez, Carlos Dafonte, Bernardino Arcay, Iciar Carricajo, Minia Manteiga