Robust design of multilayer feedforward neural networks: an experimental approach

Artificial neural networks (ANNs) have been successfully used for solving a wide variety of problems. However, determining a suitable set of structural and learning parameter values for an ANN still remains a difficult task. This article is concerned with the robust design of multilayer feedforward neural networks trained by backpropagation algorithm (Backpropagation net, BPN) and develops a systematic, experimental strategy which emphasizes simultaneous optimization of BPN parameters under various noise conditions. Unlike previous works, the present robust design problem is formulated as a Taguchi's dynamic parameter design problem, together with a fine-tuning of the BPN output when necessary. A series of computational experiments are also conducted using the data sets from various sources. From the computational results, statistically significant effects of the BPN parameters on the robustness measure (i.e., signal-to-noise ratio) are identified, based upon which an economical experimental strategy is derived. It is also shown that fine-tuning the BPN output is effective in improving the signal-to-noise ratio. Finally, the step-by-step procedures for implementing the proposed approach are illustrated with an example. (C) 2004 Elsevier Ltd. All rights reserved.
Publisher
PERGAMON-ELSEVIER SCIENCE LTD
Issue Date
2004-04
Language
ENG
Keywords

SELF-ORGANIZING MAP; TAGUCHI METHOD

Citation

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, v.17, no.3, pp.249 - 263

ISSN
0952-1976
DOI
10.1016/j.engappai.2003.12.005
URI
http://hdl.handle.net/10203/7687
Appears in Collection
IE-Journal Papers(저널논문)
Files in This Item
9.pdf(351.45 kB)Download
  • Hit : 727
  • Download : 421
  • Cited 0 times in thomson ci
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡClick to seewebofscience_button
⊙ Cited 20 items in WoSClick to see citing articles inrecords_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0