Methods of gene adaptation in case of genetically evolved artificial neural networks

• Autorzy: Chomątek, Ł.
• Języki publikacji: EN

Abstrakty

EN

Artificial neural networks are successfully applied not only for solving problems which cannot be described by mathematical formulae, but also for optimization of existing solutions. Interesting possibility for building proper neural networks can be application of evolutionary algorithms. There are three methods of preparing neural networks discussed in this article: weight-based, neuron-based and path-based adaptation. What is more, the article discusses behavior of the genetic algorithm depending on different methods of removing weights in the network.

Słowa kluczowe

PL

adaptacja wagi neuronu; ewolucja sieci neuronowych

EN

neuron weights adaptation; evolving neural networks

• Czasopismo: Metody Informatyki Stosowanej
• Rocznik: 2011
• Tom: nr 3
• Strony: 31-39
• Opis fizyczny: Bibliogr. 12 poz., rys., tab.

Twórcy

autor

Chomątek, Ł.

• Politechnika Łódzka, Wydział Fizyki Technicznej, Informatyki i Matematyki Stosowanej

Bibliografia

• [1] Sontag E. D. Feedback stabilization using two hidden layers. IEEE Transactions on Neural Networks, pp. 981-990, 1992
• [2] Bishop C. Neural Networks for Pattern Recognition. Oxford University Press, 1995
• [3] Marti L. Genetically generated neural networks. Proceedings of the International Joint Conference on Neural Networks, Baltimore, 1992
• [4] Maniezzo V. Genetic Evolution of the Topology and Weight Distribution of Neural Networks. IEEE Transactions on Neural Networks 5(1), pp. 39-53, 1994
• [5] Schiffmann W., Joost M., Werner R. Application of Genetic Algorithms to the Construction of Topologies for Multilayer Perceptrons. In : Proc. of the int. conf. Artificial Neural Nets and Genetic Algorithms, pp.675-682, 1993
• [6] Jacob C., Rehder J. Evolution of neural net architectures by a hierarchical grammarbased genetic system. In : Proceedings of International Conference on Artificial Neural Networks and Genetic Algorithms, Innsbruck, 1993
• [7] Gruau F., Whitley D., Pyeatt L. A Comparison between Cellular Encoding and Direct Encoding for Genetic Neural Networks. In : Genetic Programming 1996: Proceedings of the First Annual Conference, pp.81-89, 1996
• [8] Chomątek Ł., Rudnicki M. Application of Genetically Evolved Neural Networks to Dynamic Terrain Generation. In : XIII International Conference - System Modelling and Control, 2009
• [9] Szczepaniak P., Protasiewicz J. Price Prediction of the Electric Energy - Regression versus Neural Approach. Journal of Applied Computer Science 2(15), pp. 7-17, 2007
• [10] Niedbała G., Klejna K.: Analiza możliwości prognozowania przemieszczeń gleby podczas orki za pomocą klasycznych metod statystycznych oraz sztucznych sieci neuronowych. Inżynieria Rolnicza 2(90), 2007
• [11] D'Ambrosio D., Gregorio S., Gabriele S., Gaudio R.: A cellular automata model for soil erosion by water. Physics and Chemistry of the Earth Part B. 26, pp. 33-39, 2001
• [12] Beneˇs B., Forsbach R.: Visual Simulation of Hydraulic Erosion. Journ. of WSCG, pp. 79-86, 1994