info presentación miembros líneas investigación publicaciones investigación tesis docencia

[Articulos Revista] [Articulos Congreso] [Reports] [Libros] [Capitulos Libro] [Todo] [Resumen]

Categoria WoS
Titulo: Generation and simplification of Artificial Neural networks by means of Genetic Programming
Tipo: revista nacional
Fecha: 8,2010
Revista: Neurocomputing
JCR Journal; Impact Factor: 1.440
Volumen: 73
Paginas: 3200-3223
ISSN: 0925-2312
Editorial: Elsevier


The development of Artificial Neural Networks (ANNs) is traditionally a slow process in which human experts are needed to experiment on differen tarchitectural procedures until they find the one that presents the correct results that solvea specific problem. This work describes a new technique that uses Genetic Programming(GP) in order to automatically develop simple ANNs, with a low number of neurons and connections. Experiments havebeencarriedoutinordertomeasurethebehaviorofthe systemandalsotocomparetheresultsobtainedusingotherANNgenerationandtrainingmethodswith evolutionarycomputation(EC)tools.Theobtainedresultsare,intheworstcase,atleastcomparableto existingtechniquesand,inmanycases,substantiallybetter.Asexplainedherein,thesystemhasother importantfeaturessuchasvariablediscrimination,whichprovidesnewinformationontheproblemsto be solved. doi:10.1016/j.neucom.2010.05.010

    .: SABIA :.  Sistemas Adaptativos y Bioinspirados en Inteligencia Artificial