Filtern
Schlagworte
- computer clusters (4)
- parallel algorithms (3)
- artifcial neural networks (2)
- artificial neural networks (2)
- Neuronales Netz (1)
- Wechselkursänderung (1)
- activation functions of neurons (1)
- adaptive resonance theory (1)
- artiffficial neural networks (1)
- artififfcial neural networks (1)
- blood analysis (1)
- classification (1)
- currency exchange rates (1)
- estimation of algorithm efficiency (1)
- gradient method of training weight coefficients (1)
- information system (1)
- mathematical model (1)
- parallel calculations (1)
- social object (1)
- social simulation (1)
- time series (1)
Institut
This paper describes results of the simulation of social objects, the dependence of schoolchildren's professional abilities on their personal characteristics. The simulation tool is the artificial neural network (ANN) technology. Results of a comparison of the time expense for training the ANN and for calculating the weight coefficients with serial and parallel algorithms, respectively, are presented.