Modular Neural Networks in Assembler Encoding
Naval University, ul. Śmidowicza 69, Gdynia, Poland
T.Praczyk@amw.gdynia.pl
Received:
Received: 23 March 208; revised 16 May 2008, accepted: 21 May 2008, published online: 3 June 2008
DOI: 10.12921/cmst.2008.14.01.27-38
OAI: oai:lib.psnc.pl:643
Abstract:
Assembler Encoding represents Artificial Neural Network in a form of a simple program called Assembler Encoding Program. The task of the program is to create the so-called Network Definition Matrix which maintains all the information necessary to construct a neural network. To generate Assembler Encoding Programs and in consequence neural networks evolutionary techniques are used. The paper addresses the problem of creating modular neural networks in Assembler Encoding. The paper discusses different methods used in Assembler Encoding for this purpose. The methods are described and analyzed in terms of their effectiveness and frequency of use in Assembler Encoding Programs.
Key words:
References:
[1] F. Gruau, Neural network Synthesis Using Cellular Encoding And The Genetic Algorithm, PhD Thesis, Ecole Normale Superieure de Lyon (1994).
[2] T. Haynes and S. Sen, Co-adaptation in a team, International Journal of Computational Intelligence and Organizations, 1(4) (1996).
[3] T. Haynes and S. Sen, Evolving behavioral strategies in predators and prey. Lecture Notes in Computer Science 113-126 (1996).
[4] T. Haynes and S. Sen, Crossover operators for evolving a team, In: Proceedings of Genetic Programming 1997: The Second Annual Conference 162-167 (1997).
[5] K. Krawiec and B. Bhanu, Visual Learning by Coevolutionary Feature Synthesis, IEEE Trans. on Systems, Man, and Cybernetics, Part B: Cybernetics 35, 409-425 (2005).
[6] G Miller and D. Cliff, Co-evolution of pursuit and evasion: Biological and game-theoretic foundations, Technical Report CSRP311, School of Cognitive and Computing Sciences, University of Sussex, UK (1994).
[7] G. F. Miller, P. M. Todd and 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).
[8] P. Nordin, W. Banzhaf and F. Francone, Efficient Evolution of Machine Code for {CISC} Architectures using Blocks and Homologous Crossover, Advances in Genetic Programming III, MIT Press, L. Spector, W. Langdon, U. O’Reilly and P. Angeline 275-299 (1999).
[9] M. Potter, The Design and Analysis of a Computational Model of Cooperative Coevolution, PhD thesis, George Mason University, Fairfax, Virginia (1997).
[10] M. Potter and K. A. De Jong, Evolving neural networks with collaborative species, In: T. I. Oren, L. G. Birta (Eds.), Proceedings of the 1995 Summer Computer Simulation Conference, 340-345. The Society of Computer Simulation (1995).
[11] M. A. Potter and K. A. De Jong, A Cooperative Coevolutionary Approach to Function Optimization, The Third Parallel Problem Solving From Nature, Jerusalem, Israel,
[12] M. A. Potter and K. A. De Jong, Cooperative coevolution: An architecture for evolving coadapted subcomponents, Evolutionary Computation 8(1), 1-29 (2000).
[13] T. Praczyk, Evolving co-adapted subcomponents in Assembler Encoding, International Journal of Applied Mathematics and Computer Science 17(4) (2007).
[14] T. Praczyk, Procedure application in Assembler Encoding, Archives of Control Science 17(LIII), 1, 71-91 (2007).
[15] T. Praczyk, Using genetic algorithms and assembler encoding to generate neural networks, Computing and Informatics (2008) (in press).
[16] C. H. Yong and R. Miikkulainen, Cooperative Coevolution of Multi-Agent Systems, Technical Report AI01-287, The University of Texas at Austin (2001).
Assembler Encoding represents Artificial Neural Network in a form of a simple program called Assembler Encoding Program. The task of the program is to create the so-called Network Definition Matrix which maintains all the information necessary to construct a neural network. To generate Assembler Encoding Programs and in consequence neural networks evolutionary techniques are used. The paper addresses the problem of creating modular neural networks in Assembler Encoding. The paper discusses different methods used in Assembler Encoding for this purpose. The methods are described and analyzed in terms of their effectiveness and frequency of use in Assembler Encoding Programs.
Key words:
References:
[1] F. Gruau, Neural network Synthesis Using Cellular Encoding And The Genetic Algorithm, PhD Thesis, Ecole Normale Superieure de Lyon (1994).
[2] T. Haynes and S. Sen, Co-adaptation in a team, International Journal of Computational Intelligence and Organizations, 1(4) (1996).
[3] T. Haynes and S. Sen, Evolving behavioral strategies in predators and prey. Lecture Notes in Computer Science 113-126 (1996).
[4] T. Haynes and S. Sen, Crossover operators for evolving a team, In: Proceedings of Genetic Programming 1997: The Second Annual Conference 162-167 (1997).
[5] K. Krawiec and B. Bhanu, Visual Learning by Coevolutionary Feature Synthesis, IEEE Trans. on Systems, Man, and Cybernetics, Part B: Cybernetics 35, 409-425 (2005).
[6] G Miller and D. Cliff, Co-evolution of pursuit and evasion: Biological and game-theoretic foundations, Technical Report CSRP311, School of Cognitive and Computing Sciences, University of Sussex, UK (1994).
[7] G. F. Miller, P. M. Todd and 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).
[8] P. Nordin, W. Banzhaf and F. Francone, Efficient Evolution of Machine Code for {CISC} Architectures using Blocks and Homologous Crossover, Advances in Genetic Programming III, MIT Press, L. Spector, W. Langdon, U. O’Reilly and P. Angeline 275-299 (1999).
[9] M. Potter, The Design and Analysis of a Computational Model of Cooperative Coevolution, PhD thesis, George Mason University, Fairfax, Virginia (1997).
[10] M. Potter and K. A. De Jong, Evolving neural networks with collaborative species, In: T. I. Oren, L. G. Birta (Eds.), Proceedings of the 1995 Summer Computer Simulation Conference, 340-345. The Society of Computer Simulation (1995).
[11] M. A. Potter and K. A. De Jong, A Cooperative Coevolutionary Approach to Function Optimization, The Third Parallel Problem Solving From Nature, Jerusalem, Israel,
[12] M. A. Potter and K. A. De Jong, Cooperative coevolution: An architecture for evolving coadapted subcomponents, Evolutionary Computation 8(1), 1-29 (2000).
[13] T. Praczyk, Evolving co-adapted subcomponents in Assembler Encoding, International Journal of Applied Mathematics and Computer Science 17(4) (2007).
[14] T. Praczyk, Procedure application in Assembler Encoding, Archives of Control Science 17(LIII), 1, 71-91 (2007).
[15] T. Praczyk, Using genetic algorithms and assembler encoding to generate neural networks, Computing and Informatics (2008) (in press).
[16] C. H. Yong and R. Miikkulainen, Cooperative Coevolution of Multi-Agent Systems, Technical Report AI01-287, The University of Texas at Austin (2001).
