Abstract
We evaluated the performance of an optimal design method for a multilayer perceptron (MLP) by using the design of experiments (DOE). In our previous work, we proposed an optimal design method for MLPs in order to determine the optimal values of such parameters as the number of neurons in the hidden layers and the learning rates. In this article, we evaluate the performance of the proposed design method through a comparison with a genetic algorithm (GA)-based design method. We target an optimal design of MLPs with six layers. We also evaluate the proposed designed method in terms of calculating the amount of optimization. Through the above-mentioned evaluation and analysis, we aim at improving the proposed design method in order to obtain an optimal MLP with less effort.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Tikk D, Koczy T, Gedeon TD (2003) A survey on universal approximation and its limits in soft computing techniques. Int J Approx Reason 185-202
Rumelhart D, Hinton G, Williams R (1986) Parallel distributed processing. MIT Press, Cambridge
Inohira E, Yokoi H (2007) An optimal design method for artificial neural networks by using the design of experiments. J Adv Comput Intell Inform 11(6):593–599
Inohira E, Yokoi H (2010) Development of an optimal design method for multilayer perceptrons by using the design of experiments (in Japanese). Proceedings of the 2010 IEICE General Conference, D-2-1
Dean A, Voss D (1999) Design and analysis of experiments. Springer, New York
Frank A, Asuncion A (2010) UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. School of Information and Computer Science, University of California, Irvine
Castullo PA, Merelo JJ, Prieto A, et al (2000) G-Prop: global optimization of multilayer perceptrons using gas. Neurocomputing 35:149–163
Leung FHF, Lam HK, Ling SH, et al (2003) Tuning of the structure and parameters of a neural network using an improved genetic algorithm. IEEE Trans Neural Networks 4(1):79–88
Yeh IC (2007) Modeling slump flow of concrete using second-order regressions and artificial neural networks. Cement Concrete Composites 29(6):474–480
Yeh IC (1998) Modeling of strength of high-performance concrete using artificial neural networks. Cement Concrete Res 28(12): 1797–1808
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was presented in part at the 16th International Symposium on Artificial Life and Robotics, Oita, Japan, January 27–29, 2011
About this article
Cite this article
Inohira, E., Yokoi, H. Evaluation of an optimal design method for a multilayer perceptron by using the design of experiments. Artif Life Robotics 16, 403–406 (2011). https://doi.org/10.1007/s10015-011-0962-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10015-011-0962-4