Comparative analysis of simulators for neural networks Joone and NeuroPh
E Zdravkova, N Nenkov
COMPUTER MODELLING & NEW TECHNOLOGIES 2016 20(1) 16-20
Faculty of Mathematics and Informatics, University of Shumen “Episkop Konstantin Preslavsky” 115, Universitetska St., Shumen 9712, Bulgaria
This paper describes a comparative analysis of two simulator neural networks - Joone and NeuroPh. Both simulators are object-oriented and java - based. The analysis seeks to show how much these two simulators are similar and how different in their characteristics, what neural networks is suitable to be made through them, what are their advantages and disadvantages, how they can be used interchangeably to give certain desired result. For the purpose of comparative analysis of both the simulator will be realized logic function, which is not among the standard, and relatively complex and is selected as a combination of several standard logical operations.