Experiments on neuroevolution and online weight adaptation in complex environments
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/33235
Título: | Experiments on neuroevolution and online weight adaptation in complex environments |
---|---|
Autor/es: | Gallego-Durán, Francisco J. | Molina-Carmona, Rafael | Llorens Largo, Faraón |
Grupo/s de investigación o GITE: | Informática Industrial e Inteligencia Artificial |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial |
Palabras clave: | Neuroevolution | Online adaptation | Complex environments |
Área/s de conocimiento: | Ciencia de la Computación e Inteligencia Artificial |
Fecha de publicación: | 2013 |
Editor: | Springer Berlin / Heidelberg |
Cita bibliográfica: | GALLEGO-DURÁN, Francisco José; MOLINA-CARMONA, Rafael; LLORENS-LARGO, Faraón. "Experiments on neuroevolution and online weight adaptation in complex environments". En: Advances in Artificial Intelligence : 15th Conference of the Spanish Association for Artificial Intelligence, CAEPIA 2013, Madrid, Spain, September 17-20, 2013, Proceedings / Concha Bielza, et al. (Eds.). Berlin : Springer, 2013. (Lecture Notes in Computer Science; 8109). ISBN 978-3-642-40642-3, pp. 131-138 |
Resumen: | Neuroevolution has come a long way over the last decade. Lots of interesting and successful new methods and algorithms have been presented, with great improvements that make the field become very promising. Concretely, HyperNEAT has shown a great potential for evolving large scale neural networks, by discovering geometric regularities, thus being suitable for evolving complex controllers. However, once training phase has finished, evolved neural networks stay fixed and learning/adaptation does not happen anymore. A few methods have been proposed to address this concern, mainly using Hebbian plasticity and/or Compositional Pattern Producing Networks (CPPNs) like in Adaptive HyperNEAT. This methods have been tested in simple environments to isolate the effectiveness of adaptation from the Neuroevolution. In spite of this being quite convenient, more research is needed to better understand online adaptation in more complex environments. This paper shows a new proposal for online weight adaptation in neuroevolved artificial neural networks, and presents the results of several experiments carried out in a race simulation environment. |
URI: | http://hdl.handle.net/10045/33235 |
ISBN: | 978-3-642-40642-3 (Print) | 978-3-642-40643-0 (Online) |
ISSN: | 0302-9743 (Print) | 1611-3349 (Online) |
DOI: | 10.1007/978-3-642-40643-0_14 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/conferenceObject |
Derechos: | The original publication is available at www.springerlink.com |
Revisión científica: | si |
Versión del editor: | http://dx.doi.org/10.1007/978-3-642-40643-0_14 |
Aparece en las colecciones: | INV - i3a - Comunicaciones a Congresos, Conferencias, etc. INV - Smart Learning - Comunicaciones a Congresos, Conferencias, etc. |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
GallegoEtAl_CAEPIA2013_final.pdf | Versión final (acceso restringido) | 266,55 kB | Adobe PDF | Abrir Solicitar una copia |
GallegoEtAl_CAEPIA2013.pdf | Preprint (acceso abierto) | 461,59 kB | Adobe PDF | Abrir Vista previa |
Todos los documentos en RUA están protegidos por derechos de autor. Algunos derechos reservados.