Total views : 324

The Multi-Objective Optimization of Complex Objects Neural Network Models


  • Siberian Federal University, Krasnoyarsk, Russian Federation


Background/Objectives: The study considers the modeling technique that applies artificial neural networks analyzing their types and functional principles. Methods: A comparative analysis of the existing methods of structural and parametric synthesis of artificial neural networks has been carried out; the practicability of applying evolutionary approach to solve this problem has been justified. Findings: The multi-objective optimization of the structure of a neural network model has been formalized, given its computational complexity. The genetic algorithm has been adjusted to solve the problems of unconditional optimization of the parameters of the neural network and of selecting its effective structure in multi-objective setting. The results of solving the practical problem prove that the application of the suggested approach can help alleviate the computational complexity of the obtained structures of artificial neural networks. Applications/Improvements: The results of the study make it possible for a decision maker to select neural network model among multiple options, given the required precision and the available computational resources.


Artificial Intelligence, Modeling, Multi-Objective Optimization, Neural Network.

Full Text:

 |  (PDF views: 247)


  • Rutkovskaya D, Pilinskiy M, Putkovskiy L. Neural networks, genetic algorithms and fuzzy systems: Translated from Polish. Moscow, Hot Line - Telecom, 2004.
  • Kruglov VV, Borisov VV. Artificial neural networks. Theory and Practice. Moscow, Hot Line - Telecom, 2002.
  • Gorban AN, Educating neural networks. Moscow, SP ParaGraf, 1990.
  • Gorban AN, Rossiev DA. Neural networks on personal computer. Novosibirsk, Nauka, 1996.
  • Komashinskiy VI, Smirnov DA, Neural networks and their application in control and communication systems. Moscow, Hot Line -Telecom, 2003.
  • Mirkes EM. Neural computer, draft standard. Novosibirsk, Nauka, 1999.
  • Aleksandr I, Morton H. An Introduction to Neural Computing. London, Chapman & Hall, 1990.
  • Girosi FT, Jones M, Poggio T. Regularization theory and neural network architecture. Neural Computation. 1995; 7:219–70.
  • Hassoun M. Fundamentals of Artificial Neural Networks. Cambridge, MA, MIT Press, 1995.
  • Muller B, Reinhardt J. Neural networks. Springer-Verlag, 1990.
  • Ossovskiy S. Neural networks for data processing: Translated from Polish by I.D. Rudnitskiy. Moscow, Finance and statistics, 2002.
  • Anderson D, McNeill G, Artificial neural networks technology. DACS report. 1992.
  • Rastrigin LA. Random search. Moscow, Znaniye, 1979.
  • Bartlett P, Downs T. Training a neural network with a genetic algorithm. Technical Report, Dept of Electrical Engineering. University of Queensland. 1990; 54–68.
  • Batishchev DI. Genetic algorithms for solving extreme problems. Textbook. Voronezh, VFTI, 1995.
  • Sergeyev SA, Makhotilo KV. Genetic algorithms in synthesis of straightforward neural networks. 13th International Conference, New information technologies in science, education and business. Proceedings. Ukraine, Crimea, Yalta - Gurzuf, 1996. p. 338–42.
  • Serov VA, Belov AV, Kholba YY. Synthesis of parameters of neural controller in adaptive control system based on genetic algorithms of multi-objective optimization. 4th International symposium, Intellectual systems. Proceedings. MIFI. Moscow. 2000; 87–9.
  • Adewuya A. New methods in genetic search with real-valued chromosomes. Master’s thesis. Cambridge, Massachusetts Institute of Technology. 1996; 115–29.
  • Booker L. Improving search in genetic algorithms. Genetic algorithms and Simulated Annealing. London, Pitman. 1987; 61–73.
  • Haupt RL, Haupt SE. Practical Genetic Algorithms. 2 ed. Wiley, 2004.
  • Janikow CZ, Clair DS. Genetic algorithms simulating nature’s methods of evolving the best design solution. IEEE Potentials. 1995 Oct; 39(14):31–5.
  • Hopfield J, Tank D. Neural computations of decisions in optimization problems. Biological Cybernetics. 1985; 52:141–52.
  • Cohon J. Multiobjective Programming and Planning. New York, John Wiley, 1978.
  • Steuer RE. Multiple Criteria Optimization. New York, John Wiley, 1986.
  • Koski J, Oscyczka A. Multi-criteria Design Optimization. Springer-Verlag, 1990.
  • Srinivas D. Multiobjective Optimization using Nondominated Sorting in Genetic Algorithms. Evolutionary Computation. 1995; 2(3):39–44.
  • Schaffer JD. Multiple objective optimization with vector evaluated genetic algorithms. An International Conference on Genetic Algorithms and Their Applications. Proceedings. Pittsburgh, PA. 1985. p. 93–100.
  • Fourman MP. Compaction of symbolic layout using genetic algorithms. The First International Conference on Genetic Algorithms and Their Applications. Proceedings. Hillsdale, NJ, Lawrence Erlbaum. 1985. p. 141–53.
  • Kursawe F. Breeding ES - first results. Seminar on Evolutionary algorithms and their applications. 1996.
  • Horn J, Nafpliotis N, Goldberg D. A niched Pareto genetic algorithm for multiobjective optimization. The First IEEE Conference on Evolutionary Computation. Proceedings. Piscataway. 1994; 1:82–7.
  • Goldberg D. Genetic algorithms in search, optimization and machine learning. Reading, MA, Addison-Wesley, 1989; 230–41.
  • Fonseca CM, Fleming PJ. Multiobjective optimization and multiple constraint handling with evolutionary algorithms - Parts I, II: A unified formulation. Technical report 564. Sheffield, UK, University of Sheffield, 1995 Jan.
  • Gonebnaya OE. Expert system of iron ore melting: PhD thesis. Krasnoyarsk, GUTsMiZ, 2004.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.