Advertisement

Automation and Remote Control

, Volume 63, Issue 1, pp 66–75 | Cite as

On Stable Estimation of the Parameters of Feedforward Neural Networks in Dealing with Biological Objects

  • N. V. Belkina
  • V. V. Krepets
  • V. V. Shakin
Article

Abstract

This work is a logical extension of the works of Shurygin over the period from 1994 to 1996 and is devoted to the development of approaches to the stable estimation of the parameters of regression models. The results obtained earlier are extended to the cases of a nonlinear regression and a feedforward neural network with one hidden layer. Theoretical results are confirmed by numerical experiments. The problem of numerical modeling consisted in the construction of a system for the prediction of a change in the Gibbs free energy (Δ G) in the course of the formation of protein-protein and protein-ligand complexes. For the training set, data on 150 complexes of a various nature are used, for which there exists an experimental estimate (Δ G). For independent variables, different rated values of the physicochemical parameters of data for complexes are used.

Keywords

Neural Network Free Energy Mechanical Engineer Regression Model Numerical Modeling 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

REFERENCES

  1. 1.
    Huber, P.J., Robust Statistics, New York: Wiley, 1981.Google Scholar
  2. 2.
    Shurygin, A.M., Regression: Choice of a Model and Stable Estimation, Avtom.Telemekh., 1996, no. 6, pp. 104–115.Google Scholar
  3. 3.
    Shurygin, A.M., Prikladnaya stokhastika: robastnost', otsenivanie, prognoz (Applied Stochastics: Robustness, Estimation, Prediction), Moscow: Finansy i Statistika, 2000.Google Scholar
  4. 4.
    Meshalkin, L.D., Ispol'zovanie vesovoi funktsii pri otsenke regressionnoi zavisimosti.Mnogomernyi statisticheskii analiz v sotsial'no-ekonomicheskikh issledovaniyakh (Use of the Weight Function in Estimation of the Regression Relation. Multidimensional Statistical Analysis in Social-Economic Investigations), Moscow: Nauka, 1974.Google Scholar
  5. 5.
    Aivazyan, S.A., Bukhshtaber, V.M., Enyukov, I.S. and Meshalkin, L.D., Prikladnaya statistika: klassi fikatsiya i snizhenie razmernosti (Applied Statistics: Classification and Reduction of the Dimension), Moscow: Finansy i Statistika, 1989.Google Scholar
  6. 6.
    Aivazyan, S.A., Enyukov, I.S., and Meshalkin, L.D., Prikladnaya statistika: issledovanie zavisimostei (Applied Statistics: Investigation of Relations), Moscow: Financy i Statistika, 1985.Google Scholar
  7. 7.
    Gorban', A.N., Algoritmy i programmy bystrogo obucheniya neironnykh setei (Algorithms and Programs of Fast Training of Neural Networks), Novosibirsk: Nauka, 1992.Google Scholar
  8. 8.
    Gorban', A.N. and Rossiev, D.A., Neironnye seti na personal'mon komp'yutere (Neural Networks on a Personal Computer), Novosibirsk: Nauka, 1996.Google Scholar

Copyright information

© MAIK “Nauka/Interperiodica” 2002

Authors and Affiliations

  • N. V. Belkina
    • 1
  • V. V. Krepets
    • 1
  • V. V. Shakin
    • 2
  1. 1.Orekhovich Research Institute of Biomedical ChemistryRussian Academy of Medical SciencesMoscowRussia
  2. 2.Computer CenterRussian Academy of SciencesMoscowRussia

Personalised recommendations