A Hybrid Cascade Neural Network with Ensembles of Extended Neo-Fuzzy Neurons and Its Deep Learning
This research contribution instantiates a framework of a hybrid cascade neural network rest on the application of a specific sort of neo-fuzzy elements and a new peculiar adaptive training rule. The main trait of the offered system is its competence to continue intensifying its cascades until the required accuracy is gained. A distinctive rapid training procedure is also covered for this case that gives the possibility to operate with nonstationary data streams in an attempt to provide online training of multiple parametric variables. A new training criterion is examined which suits for handling nonstationary objects. Added to everything else, there is always an occasion to set up (increase) an inference order and a quantity of membership relations inside the extended neo-fuzzy neuron.
KeywordsTraining procedure Data stream Computational intelligence Adaptive neuro-fuzzy system Extended neo-fuzzy neuron Membership function
Oleksii K. Tyshchenko is kindly grateful for the financial assistance of the Visegrad Scholarship Program—EaP #51700967 funded by the International Visegrad Fund (IVF).
- 1.Haykin, S.: Neural Networks and Learning Machines. Prentice Hall, Upper Saddle River (2009)Google Scholar
- 5.Delen, D.: Real-World Data Mining: Applied Business Analytics and Decision Making. Pearson FT Press, Upper Saddle River (2015)Google Scholar
- 10.Bifet, A., Gavaldà, R., Holmes, G., Pfahringer, B.: Machine Learning for Data Streams with Practical Examples in MOA. The MIT Press, Cambridge (2018)Google Scholar
- 13.Menshawy, A.: Deep Learning By Example: A Hands-On Guide to Implementing Advanced Machine Learning Algorithms and Neural Networks. Packt Publishing Limited, Birmhingham (2018)Google Scholar
- 14.Fahlman, S., Lebiere, C.: The cascade-correlation learning architecture. Adv. Neural. Inf. Process. Syst. 2, 524–532 (1990)Google Scholar
- 15.Yamakawa, T., Uchino, E., Miki, T., Kusanagi, H.: A neo fuzzy neuron and its applications to system identification and prediction of the system behavior. In: Proceedings of 2nd International Conference on Fuzzy Logic and Neural Networks, pp. 477–483 (1992)Google Scholar
- 16.Miki, T., Yamakawa, T.: Analog implementation of neo-fuzzy neuron and its on-board learning. In: Computational Intelligence and Applications, pp. 144–149. WSES Press, Piraeus (1999)Google Scholar
- 19.Bodyanskiy, Ye., Tyshchenko, O.: A hybrid cascade neural network with ensembles of extended neo-fuzzy neurons and its deep learning. In: Kulczycki, P., Kowalski, P.A., Łukasik, S. (eds.) Contemporary Computational Science, p. 76. AGH-UST Press, Cracow (2018)Google Scholar
- 20.Bodyanskiy, Ye, Tyshchenko, O., Kopaliani, D.: An extended neo-fuzzy neuron and its adaptive learning algorithm. Int. J. Intell. Syst. Appl. (IJISA) 7(2), 21–26 (2015)Google Scholar
- 21.Jang, J.-S.R., Sun, C.T., Mizutani, E.: Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence. Prentice Hall, New Jersey (1997)Google Scholar
- 24.Wang, L.X.: Adaptive Fuzzy Systems and Control. Design and Stability Analysis. Prentice Hall, Upper Saddle River (1994)Google Scholar
- 28.Bodyanskiy, Ye.V., Boryachok, M.D.: Optimal control of stochastic objects under conditions of uncertainty. ISDO, Kyiv (1993)Google Scholar