Organization of the evolutionary process responsible for creating neural networks in assembler encoding

• Autorzy: Praczyk T.

Warianty tytułu

PL

Organizacja procesu ewolucyjnego w kodowaniu asemblerowym

• Języki publikacji: EN

Abstrakty

EN

Assembler Encoding (AE) represents Artificial Neural Network (ANN) in the form of a simple program called Assembler Encoding Program (AEP). The task of AEP is to create the socalled Network Definition Matrix (NDM) including all the information necessary to construct ANN. AEPs and in consequence ANNs are formed by means of evolutionary techniques. To make AE an effective tool for creating ANNs it is necessary to appropriately organize all the evolutionary processes responsible for generating AEPs, i.e., it is necessary to properly select values of different parameters controlling the evolutionary process mentioned. To determine optimal conditions of the evolution in AE, experiments in a predator-prey problem were performed. The results of the experiments are presented at the end of the paper.

PL

Kodowanie asemblerowe jest metodą wykorzystującą metody ewolucyjne do tworzenia sieci neuronowych. W kodowaniu asemblerowym sieci neuronowe ewoluują w wielu oddzielnych populacjach. Stworzenie pojedynczej sieci neuronowej wymaga połączenia elementów pochodzących z różnych populacji. Aby sieci neuronowe tworzone w ten sposób były wysokiej jakości konieczne jest odpowiednie sterowanie ewolucją w każdej populacji. Artykuł prezentuje wyniki badań, których głównym celem było określenie zasad prowadzenia ewolucji w Kodowaniu Asemblerowym.

Słowa kluczowe

EN

evolutionary neural networks

PL

ewolucyjne sieci neuronowe

• Wydawca: Wojskowa Akademia Techniczna im. Jarosława Dąbrowskiego
• Czasopismo: Biuletyn Wojskowej Akademii Technicznej
• Rocznik: 2009
• Tom: Vol. 58, nr 2
• Strony: 103--122
• Opis fizyczny: Bibliogr. 23 poz., tab., wykr.

Twórcy

autor

Praczyk T.

• Naval University, 81-103 Gdynia, Śmidowicza 69, Poland

Bibliografia

• [1] M. Alden, A. Van Kesteren, R. Miikkulainen, Eugenic Evolution Utilizing a Domain Model. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2002), San Francisco, CA, Morgan Kaufmann, 2002.
• [2] M. V. Butz, Rule - based Evolutionary Online Learning Systems: Learning Bounds, Classification, and Prediction, University of Illinois, IlliGAL Report no. 2004034, 2004.
• [3] A. Cangelosi, D. Parisi, S. Nolfi, Cell division and migration in a genotype for neural networks, Network: computation in neural systems, 5, 4, 1994, 497-515.
• [4] D. Curran, C. O'Riordan, Applying Evolutionary Computation to Designing Networks: A Study of the State of the Art, National University of Ireland, technical report NUIG-IT-111002, 2002.
• [5] D. Floreano, J. Urzelai, Evolutionary robots with online self - organization and behavioural fitness, Neural Networks, vol. 13, 2000, 431-443.
• [6] D. E. Goldberg, Genetic algorithms in search, optimization and machine learning, Addison Wesley, Reading, Massachusetts, 1989.
• [7] F. Gruau, Neural network Synthesis Using Cellular Encoding and The Genetic Algorithm, PhD Thesis, Ecole Normale Superieure de Lyon, 1994.
• [8] H. Kitano, Designing neural networks using genetic algorithms with graph generation system, Complex Systems, vol. 4, 1990, 461-476.
• [9] K. Krawiec, B. Bhanu, Visual Learning by Coevolutionary Feature Synthesis. IEEE Trans. On Systems, Man, and Cybernetics, Part B: Cybernetics, vol. 35, 2005, 409-425.
• [10] S. Luke, L. Spector, Evolving Graphs and Networks with Edge Encoding: Preliminary Report, In John R. Koza, ed., Late Breaking Papers at the Genetic Programming 1996 Conference, Stanford University, CA, USA, Stanford Bookstore, 1996, 117-124.
• [11] M. Mandischer, Representation and Evolution of Neural Networks, in Albrecht R. F., Reeves, C. R., Steele U. C., ed., Artificial Neural Nets and Genetic Algorithms, Springer Verlag, New York, 1993, 643-649.
• [12] G. F. Miller, P. M. Todd, S. U. Hegde, Designing Neural Networks Using Genetic Algorithms, Proceedings of the Third International Conference on Genetic Algorithms, 379-384 of Schaffer J. D., 1989.
• [13] D. E. Moriarty, Symbiotic Evolution of Neural Networks in Sequential Decision Tasks, PhD thesis, The University of Texas at Austin, TR UT-AI97-257, 1997.
• [14] S. Nolfi, D. Parisi, Growing neural networks, in C. G. Langton, ed., Artificial Life III, Addison-Wesley, 1992.
• [15] P. Nordin, W. Banzhaf, F. Francone, Efficient Evolution of Machine Code for (CISC) Architectures using Blocks and Homologous Crossover, Advances in Genetic Programming III, L. Spector and W. Langdon and U. O'Reilly and P. Angeline, 1999, 275-299.
• [16] D. Polani, R. Miikkulainen, Eugenic Neuro - Evolution for Reinforcement Learning, in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2000), Las Vegas, NV, 2000.
• [17] M. Potter, The Design and Analysis of a Computational Model of Cooperative Coevolution, PhD thesis, George Mason University, Fairfax, Virginia, 1997.
• [18] M. Potter, K. A. De Jong, Evolving neural networks with collaborative species, in T. I. Oren, L. G. Birta, ed., Proceedings of the 1995 Summer Computer Simulation Conference, 1995, 340-345.
• [19] T. Praczyk, Evolving co adapted subcomponents in Assembler Encoding, International Journal of Applied Mathematics and Computer Science, 17, 4, 2007.
• [20] T. Praczyk, Procedure application in Assembler Encoding, Archives of Control Science, vol. 17, 53, no. 1, 2007, 71-91.
• [21] T. Praczyk, Using genetic algorithms and assembler encoding to generate neural networks, Computing and Informatics, 2008 (in press).
• [22] T. Praczyk, Modular networks in Assembler Encoding, Computational Methods in Science and Technology, CMST 14, 1, 27-38.
• [23] J. W. Prior, Eugenic Evolution for Combinatorial Optimization, Master's thesis, The University of Texas at Austin, TR AI98-268, 1998.