Scientific and Technical Journal

ELECTROTECHNIC AND COMPUTER SYSTEMS

ISSN Print 2221-3937
ISSN Online 2221-3805
NEURAL NETWORK LEARNING METHOD BASED ON ANT COLONY ALGORITHM FOR CLASSIFICATION PROBLEMS SOLUTION
Abstract:

The original hybrid algorithm of the artificial neural network training on the basis of the ant colony algorithm and the back propagation algorithm, having essential differences from base classical ones is suggested. The algorithm testing was carried out on a public test database of the UCI Machine Learning Repository resource.

Authors:
Keywords
DOI
References
  1. Galushkin, A. I. Multilayered systems synthesis of images recognition / A. I. Galushkin. – Moscow : Energy, 1974[in Russian].
  2. Kotlyarov E. V. Hybrid training method of artificial neural network on the basis of the modified ant algorithm / E. V. Kotlyarov, T. I. Petrushina // Eastern-European Jornal of Enterprise Technologies. – 2012. –№ 5/4 (59). – Р. 16–21 [in Russian].
  3. Simon Haykin, Neural Networks: A Comprehensive Foundation (2nd Edition) / Simon Haykin – Prentince Hall, Upper Saddle River, New Jersey, 1999[in English].
  4. M.Tim Jones AI Application Programming – Charles River Media, inc, Hingham, Massachusetts, 2003 [in English].
  5. Evolving Neural Networks Using the Hybrid of Ant Colony Optimization and BP Algorithms, Advances in Neural Networks – ISNN 2006 / Lecture Notes in Computer Science, 2006, Volume 3971/2006, 714-722, DOI: 10.1007/11759966_105 [in English].
  6. Machine Learning Repository, базаданных [Электронныйресурс] / Режимдоступакбазе:

http://archive.ics.uci.edu/ml/datasets/Acute+Inflammations [inEnglish].

  1. Neural Network Based on Ant Colony Clustering Algorithm Applied to Predict the Stability of the Roof in Coal Mining, ISDA '06 Proceedings of the Sixth International Conference on Intelligent Systems Design and Applications – Vol. 01, 2006[in English].
  2. Study on the Feed forward Neural Network Based on Ant Colony Optimization / Journal of Wuhan University of Technology [Transportation Science & Engineering], 2009-03[in English].
  3. Werbos, P.J. Beyond regression: New tools for prediction and analysis in the behavioral sciences. Ph.D. thesis, Harvard University, Cambridge, MA, 1974 [in English]
Published:
Last download:
2017-11-16 11:39:38

[ © KarelWintersky ] [ All articles ] [ All authors ]
[ © Odessa National Polytechnic University, 2014. Any use of information from the site is possible only under the condition that the source link! ]
Яндекс.Метрика