Paper Info
Title
Modular neural network programming with genetic optimization
Abstract
This study proposes a modular neural network (MNN) that is designed to accomplish both artificial intelligent prediction and programming. Each modular element adopts a high-order neural network to create a formula that considers both weights and exponents. MNN represents practical problems in mathematical terms using modular functions, weight coefficients and exponents. This paper employed genetic algorithms to optimize MNN parameters and designed a target function to avoid over-fitting. Input parameters were identified and modular function influences were addressed in manner that significantly improved previous practices. In order to compare the effectiveness of results, a reference study on high-strength concrete was adopted, which had been previously studied using a genetic programming (GP) approach. In comparison with GP, MNN calculations were more accurate, used more concise programmed formulas, and allowed the potential to conduct parameter studies. The proposed MNN is a valid alternative approach to prediction and programming using artificial neural networks.
Year
DOI
Venue
2011
10.1016/j.eswa.2011.02.147
Expert Syst. Appl.
Keywords
Field
DocType
high order neural network,genetic programming,artificial intelligence,high-order neural network,proposed mnn,modular neural network programming,modular element,concrete,artificial neural network,modular function influence,genetic optimization,mnn calculation,mnn parameter,modular neural network,modular function,artificial intelligent,genetic algorithm,genetics,neural network
Modular form,Computer science,Modular neural network,Genetic programming,Time delay neural network,Artificial intelligence,Modular design,Artificial neural network,Machine learning,Genetic algorithm
Journal
Volume
Issue
ISSN
38
9
Expert Systems With Applications
Citations 
PageRank 
References 
6
0.47
8
Authors
2
Name
Order
Citations
PageRank
Hsing-Chih Tsai119114.26
Yong-Huang Lin21369.40