Copyright Statement: This is an open access article licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, even commercially as long as the original work is properly cited.
Digital Object Identifier (DOI) : 10.14569/IJACSA.2016.070155
Article Published in International Journal of Advanced Computer Science and Applications(IJACSA), Volume 7 Issue 1, 2016.
Abstract: This paper describes construction of multilayer perceptron by open source neural networks simulator - Neuroph and Petri net. The described multilayer perceptron solves logical function "xor "- exclusive or. The aim is to explore the possibilities of description of the neural networks by Petri Nets. The selected neural network (multilayer perceptron) allows to be seen clearly the advantages and disadvantages of the realizing through simulator. The selected logical function does not have a linear separability. After consumption of a neural network on a simulator was investigated implementation by Petri Nets. The results are used to determine and to consider opportunities for different discrete representations of the same model and the same subject area.
Nayden Valkov Nenkov and Elitsa Zdravkova Spasova, “Implementation of a Neural Network Using Simulator and Petri Nets*” International Journal of Advanced Computer Science and Applications(IJACSA), 7(1), 2016. http://dx.doi.org/10.14569/IJACSA.2016.070155