Search

Show simple item record

dc.contributor.authorGolovko, V.ru
dc.contributor.authorDunets, A.ru
dc.contributor.authorSavitsky, Y.ru
dc.coverage.spatialBrestru
dc.date.accessioned2021-07-27T08:09:33Z
dc.date.available2021-07-27T08:09:33Z
dc.date.issued1999
dc.identifier.citationGolovko, V. The Training of Feed-Forward Neural Networks / V. Golovko, A. Dunets, Y. Savitsky // International Conference on Neural Networks and Artificial Intelligence ICNNAI'99 = Международная конференция по нейронным сетям и искусственному интеллекту ICNNAI'99 : Proceedings, Brest, Belarus, 12–15 October 1999 / Brest Polytechnic Institute, Department of Computers and Laboratory of Artificial Neural Networks, Belarus Special Interest Group of International Neural NetWork Society, International Neural NetWork Society, Belarusian State University of Informatics and Radioelectronics (Belarus), Belarusian Academy of Sciences, Institute of Engineering Cybemetics (Belarus), Universidad Politechnica de Valencia (Spain), Institute of Computer Information Technologies (Ukraine, Ternopil) ; ed. V. Golovko. – Brest : BPI, 1999. – P. 36–39.ru
dc.identifier.urihttps://rep.bstu.by/handle/data/20667
dc.description.abstractThe training of multilayer perceptron is generally a difficult task. Excessive training times and lack of convergence to an acceptable solution are frequently reported. This paper discribes new training methods of feedforward neural networks. In comparison with standard backpropagation algorithm it has smaller time complexity and better convergence. The testing of the proposed algorithm was carried out on a coding Information task. The results of experiments are discussed.ru
dc.language.isoenru
dc.publisherBPIru
dc.titleThe Training of Feed-Forward Neural Networksru
dc.typeНаучный доклад (Working Paper)ru


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record