IDEAS home Printed from https://ideas.repec.org/a/eee/jomega/v25y1997i1p123-133.html
   My bibliography  Save this article

Neural networks: a need for caution

Author

Listed:
  • Curry, B.
  • Morgan, P.

Abstract

This paper deals with the computational aspects of neural networks. Specifically, it is suggested that the now traditional method of backpropagation (BP) may not be the most appropriate basis for learning. The argument is based on the known deficiencies of gradient descent methods, of which BP is an application. Simulation results also suggest that improved performance may be obtained by employing direct optimization procedures such as the polytope algorithm. The main reason for such performance differences appears to be that the root mean square function is subject to narrow 'valleys' and other anomalies.

Suggested Citation

  • Curry, B. & Morgan, P., 1997. "Neural networks: a need for caution," Omega, Elsevier, vol. 25(1), pages 123-133, February.
    • Handle: RePEc:eee:jomega:v:25:y:1997:i:1:p:123-133
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0305-0483(96)00052-7
    Download Restriction: Full text for ScienceDirect subscribers only
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Hung, Ming S. & Denton, James W., 1993. "Training neural networks with the GRG2 nonlinear optimizer," European Journal of Operational Research, Elsevier, vol. 69(1), pages 83-91, August.
    2. Altman, Edward I. & Marco, Giancarlo & Varetto, Franco, 1994. "Corporate distress diagnosis: Comparisons using linear discriminant analysis and neural networks (the Italian experience)," Journal of Banking & Finance, Elsevier, vol. 18(3), pages 505-529, May.
    3. McClelland, John W. & Wetzstein, Michael E. & Musser, Wesley N., 1986. "Returns To Scale And Size In Agricultural Economics," Western Journal of Agricultural Economics, Western Agricultural Economics Association, vol. 11(2), pages 1-5, December.
    4. Chiang, W. -C. & Urban, T. L. & Baldridge, G. W., 1996. "A neural network approach to mutual fund net asset value forecasting," Omega, Elsevier, vol. 24(2), pages 205-215, April.
    5. Nicholas Wilson & Kwee Chong & Michael Peel & A. N. Kolmogorov, 1995. "Neural Network Simulation and the Prediction of Corporate Outcomes: Some Empirical Findings," International Journal of the Economics of Business, Taylor & Francis Journals, vol. 2(1), pages 31-50.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Pendharkar, Parag C., 2002. "A computational study on the performance of artificial neural networks under changing structural design and data distribution," European Journal of Operational Research, Elsevier, vol. 138(1), pages 155-177, April.
    2. repec:lan:wpaper:4839 is not listed on IDEAS
    3. Chiroma, Haruna & Abdulkareem, Sameem & Herawan, Tutut, 2015. "Evolutionary Neural Network model for West Texas Intermediate crude oil price prediction," Applied Energy, Elsevier, vol. 142(C), pages 266-273.
    4. repec:lan:wpaper:4407 is not listed on IDEAS
    5. repec:lan:wpaper:4535 is not listed on IDEAS
    6. Pendharkar, Parag C., 2001. "An empirical study of design and testing of hybrid evolutionary-neural approach for classification," Omega, Elsevier, vol. 29(4), pages 361-374, August.
    7. West, David A. & Mangiameli, Paul M. & Chen, Shaw K., 1999. "Control of complex manufacturing processes: a comparison of SPC methods with a radial basis function neural network," Omega, Elsevier, vol. 27(3), pages 349-362, June.
    8. Curry, Bruce, 2004. "'Simple' neural networks for forecasting," Omega, Elsevier, vol. 32(2), pages 97-100, April.
    9. Curry, B. & Morgan, P.H., 2006. "Model selection in Neural Networks: Some difficulties," European Journal of Operational Research, Elsevier, vol. 170(2), pages 567-577, April.
    10. Murugan Anandarajan & Picheng Lee & Asokan Anandarajan, 2001. "Bankruptcy prediction of financially stressed firms: an examination of the predictive accuracy of artificial neural networks," Intelligent Systems in Accounting, Finance and Management, John Wiley & Sons, Ltd., vol. 10(2), pages 69-81, June.
    11. Gupta, Jatinder N. D. & Sexton, Randall S., 1999. "Comparing backpropagation with a genetic algorithm for neural network training," Omega, Elsevier, vol. 27(6), pages 679-684, December.
    12. Zhang, Gioqinang & Hu, Michael Y., 1998. "Neural network forecasting of the British Pound/US Dollar exchange rate," Omega, Elsevier, vol. 26(4), pages 495-506, August.
    13. Curry, B. & Morgan, P. H., 2004. "Evaluating Kohonen's learning rule: An approach through genetic algorithms," European Journal of Operational Research, Elsevier, vol. 154(1), pages 191-205, April.
    14. Geraint Johnes, 2005. "‘Don’t Know Much About History…’: Revisiting the Impact of Curriculum on Subsequent Labour Market Outcomes," Bulletin of Economic Research, Wiley Blackwell, vol. 57(3), pages 249-271, July.
    15. repec:lan:wpaper:4408 is not listed on IDEAS
    16. G Johnes, 2003. "Curriculum," Working Papers 541985, Lancaster University Management School, Economics Department.
    17. Michael Dietrich, 2006. "Neural networks and the evolution of firms and industries: An application to UK SIC34 and SIC72," Working Papers 2006007, The University of Sheffield, Department of Economics, revised May 2006.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Michael Dietrich, 2006. "Neural networks and the evolution of firms and industries: An application to UK SIC34 and SIC72," Working Papers 2006007, The University of Sheffield, Department of Economics, revised May 2006.
    2. Zhang, Guoqiang & Eddy Patuwo, B. & Y. Hu, Michael, 1998. "Forecasting with artificial neural networks:: The state of the art," International Journal of Forecasting, Elsevier, vol. 14(1), pages 35-62, March.
    3. Indro, D. C. & Jiang, C. X. & Patuwo, B. E. & Zhang, G. P., 1999. "Predicting mutual fund performance using artificial neural networks," Omega, Elsevier, vol. 27(3), pages 373-380, June.
    4. Zhang, Guoqiang & Y. Hu, Michael & Eddy Patuwo, B. & C. Indro, Daniel, 1999. "Artificial neural networks in bankruptcy prediction: General framework and cross-validation analysis," European Journal of Operational Research, Elsevier, vol. 116(1), pages 16-32, July.
    5. Adam Fadlalla & Chien-Hua Lin, 2001. "An Analysis of the Applications of Neural Networks in Finance," Interfaces, INFORMS, vol. 31(4), pages 112-122, August.
    6. Jahangoshai Rezaee, Mustafa & Jozmaleki, Mehrdad & Valipour, Mahsa, 2018. "Integrating dynamic fuzzy C-means, data envelopment analysis and artificial neural network to online prediction performance of companies in stock exchange," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 489(C), pages 78-93.
    7. Harlan Platt & Marjorie Platt, 2002. "Predicting corporate financial distress: Reflections on choice-based sample bias," Journal of Economics and Finance, Springer;Academy of Economics and Finance, vol. 26(2), pages 184-199, June.
    8. Zhou, Fanyin & Fu, Lijun & Li, Zhiyong & Xu, Jiawei, 2022. "The recurrence of financial distress: A survival analysis," International Journal of Forecasting, Elsevier, vol. 38(3), pages 1100-1115.
    9. Modina, Michele & Pietrovito, Filomena & Gallucci, Carmen & Formisano, Vincenzo, 2023. "Predicting SMEs’ default risk: Evidence from bank-firm relationship data," The Quarterly Review of Economics and Finance, Elsevier, vol. 89(C), pages 254-268.
    10. Fougère, D. & Golfier, C. & Horny, G. & Kremp, E., 2013. "What has been the impact of the 2008 crisis on firms’ default? (in French)," Working papers 463, Banque de France.
    11. Fabio Panetta & Fabiano Schivardi & Matthew Shum, 2009. "Do Mergers Improve Information? Evidence from the Loan Market," Journal of Money, Credit and Banking, Blackwell Publishing, vol. 41(4), pages 673-709, June.
    12. Francesco Ciampi & Alessandro Giannozzi & Giacomo Marzi & Edward I. Altman, 2021. "Rethinking SME default prediction: a systematic literature review and future perspectives," Scientometrics, Springer;Akadémiai Kiadó, vol. 126(3), pages 2141-2188, March.
    13. Jie Sun & Jie Li & Hamido Fujita & Wenguo Ai, 2023. "Multiclass financial distress prediction based on one‐versus‐one decomposition integrated with improved decision‐directed acyclic graph," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 42(5), pages 1167-1186, August.
    14. Beynon, Malcolm J. & Peel, Michael J., 2001. "Variable precision rough set theory and data discretisation: an application to corporate failure prediction," Omega, Elsevier, vol. 29(6), pages 561-576, December.
    15. Yu Sheng & Shiji Zhao & Katarina Nossal & Dandan Zhang, 2015. "Productivity and farm size in Australian agriculture: reinvestigating the returns to scale," Australian Journal of Agricultural and Resource Economics, Australian Agricultural and Resource Economics Society, vol. 59(1), pages 16-38, January.
    16. Haider A. Khan, 2004. "General Conclusions: From Crisis to a Global Political Economy of Freedom," Palgrave Macmillan Books, in: Global Markets and Financial Crises in Asia, chapter 9, pages 193-211, Palgrave Macmillan.
    17. Mishra, Sasmita & Padhy, Sudarsan, 2019. "An efficient portfolio construction model using stock price predicted by support vector regression," The North American Journal of Economics and Finance, Elsevier, vol. 50(C).
    18. Hyytinen, Ari, 2003. "Information production and lending market competition," Journal of Economics and Business, Elsevier, vol. 55(3), pages 233-253.
    19. Philip Swicegood & Jeffrey A. Clark, 2001. "Off‐site monitoring systems for predicting bank underperformance: a comparison of neural networks, discriminant analysis, and professional human judgment," Intelligent Systems in Accounting, Finance and Management, John Wiley & Sons, Ltd., vol. 10(3), pages 169-186, September.
    20. Arthur Charpentier & Emmanuel Flachaire & Antoine Ly, 2017. "Econom\'etrie et Machine Learning," Papers 1708.06992, arXiv.org, revised Mar 2018.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:jomega:v:25:y:1997:i:1:p:123-133. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/375/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.