Abstract
In this chapter the first technology of CI-neural networks is considered. In the Sect. 1.2 neural network Back propagation (NN BP) is considered which is most widely used, its architecture and functions described. The important theorem on universal approximation for NN BP is considered which grounds its universal applications in forecasting, pattern recognition, approximation etc. gradient method of training neural network BP is described, its properties analyzed in Sect. 1.3. In Sect. 1.4 the extension of gradient algorithm for training NN BP with arbitrary number of layers is considered. In Sect. 1.5 some modifications of gradient algorithm improving its properties are described. In Sect. 1.6 method of conjugate gradient is considered for network training which has accelerated convergence as compared with conventional gradient method. In Sect. 1.7 genetic algorithm for training NNBP is considered, its properties are analyzed. In Sect. 1.8 is presented another class of widely used neural networks with radial basis functions . Its structure and properties are described and analyzed. Methods of training weights and parameters of radial functions are considered. The more general class of radial neural networks- so-called Hyper Radial Basis Function networks (HRBF) is considered, its properties are described and analyzed. In Sect. 1.9 efficient algorithm of RBF network training- hybrid algorithm is presented and its properties described. In the Sect. 1.10 some examples of application RBF neural network and methods of selection the number of radial basis functions are presented, comparison of back propagation neural networks and RBF NN is performed.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Zaychenko, Yu.P.: Fundamentals of Intellectual Systems Design, p. 352. Kiev Publishing House “Slovo” (2004) (rus)
Simon, H.: Neural Networks. Full Course. 2nd edn., p. 1104 (Transl. engl.). Moscow Publishing House “Williams” (2006) (rus)
Anderson, J., Rosenfeld, E. (eds.): Neurocomputing: Foundations of Research. MIT Press, Cambridge, MA (1988)
Hornik, K., Stinchcombe M., White, H.: Multilayer feed forward networks are universal approximators. Neural Networks 2, 359–366 (1989)
Voronovsky, G.K., Makhotilo, K.V., Petrashev, S.N., Sergeyev, S.A.: Genetic Algorithms- Artificial Neural Networks and Problems of Virtual Reality, p. 212. Kharkov Publishing House “Osnova” (1997) (rus)
Korotky, S.: Neural networks: Self-learning. http://www.orc.ru (1999)
Osovsky, S.: Neural Networks for Information Processing. Finance and Statistics, p. 344 (transl. from pol.). M.: Publishing House (2002) (rus)
Batischev, D.I.: Genetic algorithms for extremal problems solution. In: Teaching Manual, p. 65, Voronezh state Technical University, Voronezh (1995) (rus)
Batischev, D.I., Isayev, S.A., Remer, E.K.: Evolutionary-genetic approach for non- convex problem optimization. In: Inter-High School Scientific Works Collection Simulation Optimization in Automated Systems, Voronezh State Technical University, Voronezh, pp. 20–28 (1998) (rus)
Batyrshyn, I.Z.: Methods of presentation and processing of fuzzy information in intellectual systems. In: Scientific Review in: News in Artificial Intelligence. Publishing RAAI Anaharsis. №2, pp. 9–65 (1996) (rus)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Zgurovsky, M.Z., Zaychenko, Y.P. (2016). Neural Networks. In: The Fundamentals of Computational Intelligence: System Approach. Studies in Computational Intelligence, vol 652. Springer, Cham. https://doi.org/10.1007/978-3-319-35162-9_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-35162-9_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-35160-5
Online ISBN: 978-3-319-35162-9
eBook Packages: EngineeringEngineering (R0)