caa a22 4500 475801040 CHVBK 20180406123737.0 cr unu---uuuuu 170329e20000201xx s 000 0 eng 10.1023/A:1009628031942 doi (NATIONALLICENCE)springer-10.1023/A:1009628031942 A Minimax Method for Learning Functional Networks [Elektronische Daten] [E. Castillo, J. Gutiírrez, A. Cobo, C. Castillo] In this paper, a minimax method for learning functional networks is presented. The idea of the method is to minimize themaximum absolute error between predicted and observed values. In addition, the invertible functions appearing in the modelare assumed to be linear convex combinations of invertible functions. This guarantees the invertibilityof the resulting approximations. The learning method leads to a linear programming problem and then: (a) the solution isobtained in a finite number of iterations, and (b) the global optimum is attained. The method is illustrated withseveral examples of applications, including the Hénon and Lozi series. The results show that the method outperforms standard least squares direct methods. Kluwer Academic Publishers, 2000 functional equations nationallicence functional networks nationallicence learning nationallicence neural networks nationallicence Castillo E. Department of Applied Mathematics and Computational Sciences, Spain aut Gutiírrez J. Department of Applied Mathematics and Computational Sciences, Spain aut Cobo A. Department of Applied Mathematics and Computational Sciences, Spain aut Castillo C. Ocean and Coastal Research Group, University of Cantabria, Spain aut Neural Processing Letters Kluwer Academic Publishers 11/1(2000-02-01), 39-49 1370-4621 11:1<39 2000 11 11063 https://doi.org/10.1023/A:1009628031942 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1023/A:1009628031942 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Castillo E. Department of Applied Mathematics and Computational Sciences, Spain aut NATIONALLICENCE 700 1- Gutiírrez J. Department of Applied Mathematics and Computational Sciences, Spain aut NATIONALLICENCE 700 1- Cobo A. Department of Applied Mathematics and Computational Sciences, Spain aut NATIONALLICENCE 700 1- Castillo C. Ocean and Coastal Research Group, University of Cantabria, Spain aut NATIONALLICENCE 773 0- Neural Processing Letters Kluwer Academic Publishers 11/1(2000-02-01), 39-49 1370-4621 11:1<39 2000 11 11063 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer