Artificial creativity in linguistics using evolvable fuzzy neural networks

Abstract

The paper describes an application of evolvable fuzzy neural networks for artificial creativity in linguistics. The task of the creation of an English vocabulary was resolved with neural networks which have an evolvable architecture with learning capabilities as well as a fuzzy connectionist structure. The paper features a form of artificial creativity which creates words on its own using genetic algorithms, fuzzy logic methods, and multiple layer neural networks. Tests of the new method are also described. © 2008 Springer-Verlag Berlin Heidelberg.