Evolutionary Design and Training of Artificial Neural Networks
The dynamics of neural networks and evolutionary algorithms share common attributes and based on many research papers it seems to be that from dynamic point of view are both systems indistinguishable. In order to compare them mutually from this point of view, artificial neural networks, as similar as possible to natural one, are needed. In this paper is described part of our research that is focused on the synthesis of artificial neural networks. Since most current ANN structures are not common in nature, we introduce a method of a complex network synthesis using network growth model, considered as a neural network. Synaptic weights of the synthesized ANN are then trained by an evolutionary algorithm to respond to an input training set successfully.
KeywordsNeural network synthesis Network growth model Complex network Evolutionary algorithms
The following grants are acknowledged for the financial support provided for this research: Grant of SGS No. 2018/177, VSB-Technical University of Ostrava and by the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 710577.
- 4.Kojecký, L., Zelinka, I., Prasad, A., Vantuch, T., Tomaszek, L.: Investigation on unconventional synthesis of astroinformatic data classificator powered by irregular dynamics. IEEE Intell. Syst. (in press)Google Scholar
- 10.Oplatková, Z.: Metaevolution-synthesis of evolutionary algorithms by means of symbolic regression. Tomas Bata University in Zlín (2008)Google Scholar
- 11.Vařacha, P.: Neural network synthesis (2011)Google Scholar
- 13.Zelinka, I.: Analytic programming by means of soma algorithm. In: Proceedings of the 8th International Conference on Soft Computing, Mendel, vol. 2, pp. 93–101 (2002)Google Scholar