Fundamentals of Artificial Neural Networks

  • Z. Waszczyszyn
Part of the CISM International Centre for Mechanical Sciences book series (CISM, volume 404)


The introduction to this Chapter concerns principal ideas of the formulation of Artificial Neural Networks (ANNs), main features of neurocomputation, its development and applications. The main attention is paid to feedforward NNs, especially to the error backpropagation algorithm and Back-Propagation Neural Networks (BPNNs). Data selection and preprocessing, learning methods, BPNN generalisation, multilayered NN architectures and radial basis functions are discussed. In the frame of unsupervised learning different learning rules are listed and their usage in Kohonen self-organizing networks, ART (Adaptive Resonanse Theory) networks and CP (Counter-Propagation) networks are considered. The Hopfield discrete and continuous networks and the BAM (Bidirectional Adaptive Memory) network are discussed as examples of recurrent neural networks. The references cover theoretical background of ANNs, review papers and selected papers on applications of neurocomputing to the analysis of problems in mechanics and structural engineering.


Hide Layer Radial Basis Function Network Synaptic Weight Hopfield Neural Network Bidirectional Associate Memory 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Rojas, R.: Neural Networks — A Systematic Introduction, Springer, Berlin/ Heidelberg 1966.Google Scholar
  2. 2.
    Haykin, S.: Neural Networks — A Comprehensive Foundations, Macmillan College Publishing Co., Englewood Cliffs, NJ 1994.Google Scholar
  3. 3.
    Fausett, L.: Fundamentals of Neural Networks — Architectures, Algorithms, and Applications, Prentice Hall Inc., Englewood Cliffs, NJ 1994.MATHGoogle Scholar
  4. 4.
    Rumelhard, D.E. and McClelland, J.L. (Eds): Parallel Distributed Processing — Explorations in the Microstructure of Cognition, Vol.1, MIT Press, Cambridge, MA 1986.Google Scholar
  5. 5.
    Adeli, H. and Yeh, C.: Perceptron learning in engineering design, Microcomputers in Civil Eng., 4 (1989), 247–256.CrossRefGoogle Scholar
  6. 6.
    Topping, B.H.V. and Khan, A.I. (Eds): Neural Networks and Combinatorial Optimization in Civil and Structural Engineering, Civil-Comp Press, Edinburgh 1993.Google Scholar
  7. 7.
    Panagiotopoulos, P.D. (Sci. Coordinator): Applications of the Neural Networks in Engineering and Medicine, STRIDE-Programm of the EEC, 1993.Google Scholar
  8. 8.
    Hajela, P. and Berke, L.: Neural networks in structural analysis and design — an overview, Computing Systems in Eng., 3(1992), 525–538.CrossRefGoogle Scholar
  9. 9.
    Waszczyszyn, Z.: Some recent and current problems of neurocomputing in civil and structural engineering, in: Advances in Computational Structures Technology (Ed. B.H. V. Topping), Civil-Comp Press, Edinburgh 1996, 43–58.CrossRefGoogle Scholar
  10. 10.
    Topping, B.H.V. and Bahreininejad, A.: Neural Computing for Structural Mechanics, Saxe-Coburg Publications, Edinburgh 1997.Google Scholar
  11. 11.
    Paez, Th. L.: Neural networks in mechanical system simulation, identification and assessment, Shock and Vibration, 1 (1993), 177–199.Google Scholar
  12. 12.
    Waszczyszyn, Z., Pabisek, E. and Mucha, G.: Hybrid neural network/ computational programs to the analysis of elastic-plastic structures, in: Discretizations Methods in Structural Mechanics (Eds. H. Mang and F.G. Rammerstorfer), Kluwer Acad. Publ., Dortrecht 1999, 189–198.CrossRefGoogle Scholar
  13. 13.
    Gunaratnam, D.J. and Gero, J.S.: Effects of representation on the performance of neural networks in structural engineering applications, Microcomputers in Civil Eng., 9 (1994), 97–108.CrossRefGoogle Scholar
  14. 14.
    Wu, X., Ghaboussi, J. and Garret, J.H.Jr.: Use of neural networks in detection of structural damage, Comp. Stru., 42 (1992), 649–659.CrossRefMATHGoogle Scholar
  15. 15.
    Stavroulakis, G.E. and Abdalla, K.M.: A systematic neural network classificator in mechanics — an application in semi-rigid steel joints, Eng. Analysis and Design, 1(1994), 272–292.Google Scholar
  16. 16.
    Pao, V.H.: Adaptative Pattern Recognition and Neural Networks, Addison-Wesley, Reading MA 1996.Google Scholar
  17. 17.
    Osowski, S.: Neural Networks (in Polish), Oficyna Wyd. Polit. Warszawskiej, Warsaw 1994.Google Scholar
  18. 18.
    Hajela, P. and Berke, L.: Neurobiological computational models in structural analysis and design, Comp. Stru., 41 (1991), 657–667.CrossRefMATHGoogle Scholar
  19. 19.
    Hertz, J., Krogh, A. and Palmer, R.G.: Introduction to the Theory of Neural Computation, Addison-Wesley, Reading MA 1991.Google Scholar
  20. 20.
    Demuth, H. and Beale, M.: Neural Network Toolbox for Use with MATLAB — User’s Guide, The Math Works, Natick MA 1994.Google Scholar
  21. 21.
    Zell, A. (Ed.): SNNS — Stuttgart Neural Network Simulator, User’s Manual, Version 4.1, Univ. Stuttgart 1995.Google Scholar
  22. 22.
    Masters, T.: Practical Neural Network Recipes in C++, Academic Press 1993.Google Scholar
  23. 23.
    Waszczyszyn, Z., Pabisek, E. and Stankiewicz, P.: Application of back-propagation neural networks to the buckling analysis of cylindrical shells, in: Neural Networks and Their Applicatios, Proc. 3rd Conf. Czestochowa, Poland, 1997, 473–478.Google Scholar
  24. 24.
    Hegazy, T., Fazio, P. and Moselhi, O.: Developing practical neural network applications using back-propagation, Microcomputers in Civil Eng., 9 (1994), 145–159.CrossRefGoogle Scholar
  25. 25.
    Cios, K.J., Vary, J., Berke, J. and Kautz, H.E.: Application of neural networks to prediction of advanced composite structures mechanical response and behaviour, Computing Systems in Eng., 3(1992), 539–544.CrossRefGoogle Scholar
  26. 26.
    Sarzeaud, O., Stephan, Y. and Touzec, C: Finite element meshing using Kohonen’s self-organizing maps, in: Artificial Neural Networks (Eds. T. Kohonen et al), Elsevier Science Publishers, 1991, 1313–1317.Google Scholar
  27. 27.
    Braspenning, P.J., Thuijsman, F. and Weijters, A. J. M. M. (Eds): Artificial Neural Networks — An Introduction to ANN Theory and Practice, Springer, Berlin/ Heidelberg 1995.MATHGoogle Scholar
  28. 28.
    Adeli, H. and Park, H.S.: Counterpropagation neural networks in structural engineering, J.of Structural Eng., 121 (1995), 1205–1212.CrossRefGoogle Scholar
  29. 29.
    Szewczyk, Z.P. and Hajela, P.: Neural network approximation in a simulated annealing based optimal structural design, Structural Optimization, 5 (1993), 159–165.CrossRefGoogle Scholar
  30. 30.
    Szewczyk, Z.P. and Hajela, P.: Damage detection in structures based on featuresensitive neural networks, J. of Computing in Civil Eng., 8 (1993), 163–178.CrossRefGoogle Scholar
  31. 31.
    Kortesis, S. and Panagiotopoulos, P.G.: Neural networks for computing in structural analysis — methods and prospects of applications, Int. J. Num. Methods in Eng., 36 (1993), 2305–2318.CrossRefMATHGoogle Scholar
  32. 32.
    Lou, K-N. and Perez, R.A.: On the artificial neural networks for structural analysis, in: Recent Advances in Structural Mechanics, ASME, PVP-295/NE-16, (1994), 149–161.Google Scholar

Copyright information

© Springer-Verlag Wien 1999

Authors and Affiliations

  • Z. Waszczyszyn
    • 1
  1. 1.Cracow University of TechnologyCracowPoland

Personalised recommendations