Evolutionary computing in operational research for two-layer neural networks

• Autorzy: Płaczek S.
• Języki publikacji: EN

Abstrakty

EN

Considering the non-linear characteristics of the activation functions, the entire task is multidimensional and non-linear with a multimodal target function. Implementing evolutionary computing in the multimodal optimization tasks gives developers new and effective tools for seeking the global minimum. A developer has to find the optimal and simple transformation between the realization of a phenotype and a genotype. In the article, a two-layer neural network is analysed. In the first step, the population is created. In the main algorithm loop, a parent selection mechanism is used together with the fitness function. To evaluate the quality of evolutionary computing process different measured characteristics are used. The final results are depicted using charts and tables.

Słowa kluczowe

EN

evolutionary algorithm; neural network; optimization algorithm; mutation operator; crossover operator

• Wydawca: Wydawnictwo Szkoły Głównej Gospodarstwa Wiejskiego w Warszawie
• Czasopismo: Information Systems in Management
• Rocznik: 2017
• Tom: Vol. 6, No. 2
• Strony: 119--130
• Opis fizyczny: Bibliogr. 6 poz., rys., wykr.

Twórcy

autor

Płaczek S.

Bibliografia

• [1] Eiben A.E., Smith J.E.: Introduction to Evolutionary Computing, Second Edition, Springer 2003, 2015.
• [2] Michalewicz Z.: Genetic Algorithm + Data Structure = Evolutionary Programs, Springer-Verlag Berlin Haidelberg 1996.
• [3] Montana DJ, Davis L.: Training Feedforward Neural Network Using Genetic Algorithms. Proceedings of the 1989 International Join Conference on Artificial Intelligence", Morgan Kaufmann Publishers, San Mateo CA 1989.
• [4] Goldberg David E.: Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Veslay Publishing Company, Inc. 1989.
• [5] Xinjie Yu, Mitsuo Gen: Introduction to Evolutionary Algorithm, Springer London 2010.
• [6] Nolfi Stefano, Floreano Dario: Evolutionary Robotics, The MIT Press, Cambridge, Massachusetts, London 2000.