Meta-Learning Evolutionary Artificial Neural Networks Using Cellular Configurations: Experimental Works

  • Asma Abu Salah
  • Yahya Al-Salqan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4113)


In this paper, we present the experimental works performed to test and explore the performance of our proposed framework: meta-learning evolutionary artificial neural network by means of cellular automata (MLEANN-CA). This framework based on evolutionary computation with direct and indirect encoding methods (cellular automata) for automatic design of optimal artificial neural networks wherein the neural network architecture, activation function, connection weights, and the learning algorithm with its parameters are adapted according to the problem. We used two toolboxes for simulations: NeuroSolutions and NeuroGenetic Optimizer besides two famous chaotic time series. We compared the performance of the proposed MLEANN-CA with the previous MLEANN framework, which used the direct encoding methods, and with the conventional design of ANNs. We demonstrated how effective is the proposed MLEANN-CA framework to obtain a design of feed-forward neural network that is smaller, faster and with better generalization performance.


Cellular Automaton Hide Node Hide Neuron Levenberg Marquardt Neural Network Architecture 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Abraham, A.: Meta-Learning Evolutionary Artificial Neural Networks. Neurocomputing Journal 56c, 1–38 (2004)Google Scholar
  2. 2.
    Abraham, A.: Optimization of Evolutionary Neural Networks Using Hybrid Learning Algorithms. In: IEEE International Conference on Neural Networks, vol. 3, pp. 2797–2802. IEEE Press, New York (2002)Google Scholar
  3. 3.
    Abu, S.A., Al-Salqan, Y.: Meta-learning Evolutionary Artificial Neural Networks: By Means of Cellular Automata. In: Proceedings of IEEE International Conference on Computational Intelligence for Modelling, Control and Automation, Vienna-Austria, IEEE press, USA (2006)Google Scholar
  4. 4.
    Bhattacharya, A., Abraham, A., Grosan, C., Vasant, P.: Meta-Learning Evolutionary Artificial Neural Network for Selecting Flexible Manufacturing Systems under Disparate Level-of-Satisfaction of Decision Maker. In: IEEE International Symposium on Neural Networks. LNCS, Springer, Heidelberg (2006)Google Scholar
  5. 5.
    Box, G.E.P., Jenkins, G.M.: Time Series Analysis, Forecasting and Control. Holden Day, San Francisco (1970)MATHGoogle Scholar
  6. 6.
    Gutierrez, G., Isasi, P., Molina, J.M., Sanchis, A., Galvan, I.M.: Evolutionary cellular configurations for designing feed-forward neural networks architectures. In: Mira, J., Prieto, A.G. (eds.) IWANN 2001. LNCS, vol. 2084, pp. 514–521. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  7. 7.
    Mackey, M.C., Glass, L.: Oscillation and Chaos in Physiological Control Systems. Science 197, 287–289 (1977)CrossRefGoogle Scholar
  8. 8.
    Molina, J.M., Galvan, I., Isasi, P., Sanchis, A.: Grammars and Cellular Automata for Evolving Neural Network Architectures. In: IEEE International Conference on Systems, Man, and Cybernetics, vol. 4, pp. 2497–2502 (2000)Google Scholar
  9. 9.
    Yao, X.: Evolving Artificial Neural Networks. Proceedings of IEEE 87(9), 423–447 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Asma Abu Salah
    • 1
  • Yahya Al-Salqan
    • 1
  1. 1.Computer science DepartmentAl-Quds UniversityJerusalemPalestine

Personalised recommendations