|
Archivo Abierto Institucional de la Universidad Carlos III de Madrid >
Investigación >
Departamentos >
Departamento de Informática >
Grupo de Control, Aprendizaje y Optimización de Sistemas (CAOS) >
DI - CAOS - Comunicaciones en Congresos y otros eventos >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10016/9903
|
| Title: | Generative capacities of grammars codification for evolution of NN architectures |
| Author(s): | Guinea, M.A.
Gutiérrez, Germán
Galván, Inés M.
Sanchis, Araceli
Molina, José M. |
| Publisher: | IEEE |
| Issued date: | 2002 |
| Citation: | Proceedings of the 2002 Congress on Evolutionary Computation. CEC '02, pp. 611-616. |
| URI: | http://hdl.handle.net/10016/9903 |
| ISBN: | 0-7803-7282-4 |
| DOI: | http://dx.doi.org/10.1109/CEC.2002.1006996 |
| Description: | Proceeding of: 2002 Congress on Evolutionary Computation, 2002. CEC'02, may 12-17, 2002. Honolulu, Hawaii, USA. |
| Abstract: | Designing the optimal architecture can be formulated as a search problem in the architectures space, where each point represents an architecture. The search space of all possible architectures is very large, and the task of finding the simplest architecture may be an arduous and mostly a random task. Methods based in indirect encoding have been used to reduce the chromosome length. In this work a new indirect encoding method is proposed and an analysis of the generative capacity of the method is presented. |
| Publisher version: | http://dx.doi.org/10.1109/CEC.2002.1006996 |
| Keywords: | Architectures space
Chromosome length reduction
Generative capacity
Grammar codification
Indirect encoding method
Neural net architecture evolution
Optimal neural net architecture design
Search space
Simplest architecture |
| Rights: | © IEEE |
| Appears in Collections: | DI - CAOS - Capítulos de Monografías
DI - CAOS - Comunicaciones en Congresos y otros eventos
|
Items in E-Archivo are protected by copyright, with all rights reserved, unless otherwise indicated.
|
