Neural network modeling of critical tempe-ratures for steel pitting.

• Datum: 2019
• Hauptverfasser: Korniienko, O. V., Subbotin, S. O., Naryvskyi, O. E.
• Format: Artikel
• Sprache: Ukrainisch
• Veröffentlicht: Інститут проблем реєстрації інформації НАН України 2019
• Schlagworte: dataset; training; neural network; error; gradient; dropout; probability; AiSi 321 steel
• Online Zugang: http://drsp.ipri.kiev.ua/article/view/179699
• Назва журналу: Data Recording, Storage & Processing

The task of creating mathematical software for constructing quantitative dependency models based on forward propagation neural networks has been solved in the work. A modification of method for dropping out neurons is proposed, which better prevents the model from overfitting. The modified method ta...