DocumentCode :
2347952
Title :
Multilayer neural networks training methodic
Author :
Golovko, Vladimir ; Maniakov, Nikolaj ; Makhnist, Leonid
Author_Institution :
Lab. of Artificial Intelligence, Brest State Tech. Univ.
fYear :
2003
fDate :
8-10 Sept. 2003
Firstpage :
185
Lastpage :
190
Abstract :
We propose three new techniques for training of multilayer neural networks. Its basic concept is based on the gradient descent method. For every methodic are showed formulas for calculation of the adaptive training steps. Matrix algorithmization for all of this techniques are very helpful in its program realization
Keywords :
feedforward neural nets; gradient methods; learning (artificial intelligence); adaptive training step; gradient descent method; matrix algorithmization; multilayer neural network training; program realization; Artificial intelligence; Artificial neural networks; Chaos; Feedforward neural networks; Laboratories; Least squares approximation; Mathematics; Multi-layer neural network; Neural networks; Neurons;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, 2003. Proceedings of the Second IEEE International Workshop on
Conference_Location :
Lviv
Print_ISBN :
0-7803-8138-6
Type :
conf
DOI :
10.1109/IDAACS.2003.1249545
Filename :
1249545
Link To Document :
بازگشت