Abstract
Given N data pairs {X i , y i }, i=1,2,...,N, where each X i is an n-dimensional vector of independent variables \((X_i = <x_{i_1} , x_{i_2}, \ldots,x_{i_n}>)\) and y i is a dependent variable, the function approximation problem (FAP) is finding a function that best explains the N pairs of X i and y i . From the universal approximation theorem and inherent approximation capabilities proved by various researches, artificial neural networks (ANNs) are considered as powerful function approximators. There are two main issues on the feedforward neural networks’ performance. One is to determine its structure. The other issue is to specify the weights of a network that minimizes its error. Genetic algorithm (GA) is a global search technique and is useful for complex optimization problems. So, it has been considered to have potential to reinforce the performance of neural networks. Many researchers tried to optimize the weights of networks using genetic algorithms alone or combined with the backpropagation algorithm. Others also tried to find a good topology that is even more difficult and called a “black art.”
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kwon, YK., Moon, BR. (2004). Evolving Features in Neural Networks for System Identification. In: Deb, K. (eds) Genetic and Evolutionary Computation – GECCO 2004. GECCO 2004. Lecture Notes in Computer Science, vol 3103. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24855-2_45
Download citation
DOI: https://doi.org/10.1007/978-3-540-24855-2_45
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22343-6
Online ISBN: 978-3-540-24855-2
eBook Packages: Springer Book Archive