Evaluation of an optimal design method for a multilayer perceptron by using the design of experiments |
| |
| Authors: | Eiichi Inohira and Hirokazu Yokoi |
| |
| Affiliation: | (1) Centre for Molecular, Environmental, Genetic and Analytic Epidemiology, School of Population Health, University of Melbourne, Melbourne, Victoria, Australia;(2) Mahidol-Oxford Tropical Medicine Research Unit, Faculty of Tropical Medicine, Mahidol University, Bangkok, Thailand;(3) International Health Program, Menzies School of Health Research and Charles Darwin University, Darwin, Northern Territory, Australia;(4) Centre for Clinical Vaccinology and Tropical Medicine, Churchill Hospital, Oxford, UK;(5) School of Pharmacy, University of Otago, Dunedin, New Zealand |
| |
| 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. |
| |
| Keywords: | |
| 本文献已被 SpringerLink 等数据库收录！ |
|
