| Title | Memetic algorithms to product-unit neural networks for regression |
|---|---|
| Authors | MARTÍNEZ ESTUDILLO, FRANCISCO JOSÉ, Hervás-Martínez C. , MARTÍNEZ ESTUDILLO, ALFONSO CARLOS, Ortíz-Boyer D. |
| External publication | No |
| Means | Lect. Notes Comput. Sci. |
| Scope | Conference Paper |
| Nature | Científica |
| JCR Quartile | 4 |
| SJR Quartile | 2 |
| JCR Impact | 0.402 |
| SJR Impact | 0.334 |
| Web | https://www.scopus.com/inward/record.uri?eid=2-s2.0-25144507014&doi=10.1007%2f11494669_11&partnerID=40&md5=10cb34b0c5e37c671a4055618ea82071 |
| Publication date | 01/01/2005 |
| Scopus Id | 2-s2.0-25144507014 |
| DOI | 10.1007/11494669_11 |
| Abstract | In this paper we present a new method for hybrid evolutionary algorithms where only a few best individuals are subject to local optimization. Moreover, the optimization algorithm is only applied at specific stages of the evolutionary process. The key aspect of our work is the use of a clustering algorithm to select the individuals to be optimized. The underlying idea is that we can achieve a very good performance if, instead of optimizing many very similar individuals, we optimize just a few different individuals. This approach is less computationally expensive. Our results show a very interesting performance when this model is compared to other standard algorithms. The proposed model is evaluated in the optimization of the structure and weights of product-unit based neural networks. © Springer-Verlag Berlin Heidelberg 2005. |
| Keywords | Computational complexity; Neural networks; Optimization; Regression analysis; Hybrid evolutionary algorithms; Optimization algorithms; Algorithms |
| Universidad Loyola members |