Abstract
Deep neural networks (DNN) and their generalizations—hybrid DNN are considered which represent the efficient tools for BD analysis. The properties and drawbacks of deep learning are considered and analyzed. Encoders—decoders and restricted Boltzmann machines are described and their applications for Deep learning implementation are presented. Methods of regularization of DL: penalty functions, Dropout and Bagging are presented. New class of deep learning networks are suggested and presented. so-called GMDH-neo-fuzzy networks representing a combination of self-organization method GMDH and fuzzy neural networks. Due to principle of self-organization and small number of tuning parameters GMDH enables to simplify and accelerate the training of DN. Several variants of this class hybrid networks are considered and algorithms of their structure synthesis based on GMDH are suggested and analyzed. The application of GMDH enables to reduce dimensionality of training DN and accelerate the convergence of training and by this solve some problems of Big Data Analysis. Experimental investigations of hybrid GMDH-neo-fuzzy networks are carried out and their results are presented and analyzed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
G. Hinton, S. Osindero, Y.-W. Teh, A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
I. Goodfellow, Y. Bengio, A. Courville, Deep Learning (MIT Press, 2016)
Y. Bengio, Y. LeCun, G. Hinton, Deep learning. Nature 521, 436–444 (2015)
J. Schmidhuber, Deep learning in neural networks: an overview. Neural Netw. 61
E. Lughofer, Evolving Fuzzy Systems—Methodologies, Advanced Concepts and Applications (Springer, Berlin, 2011, 2015), pp. 85–117
Z. Hu, Y.V. Bodyanskiy, O.K. Tyshchenko, A cascade deep neuro-fuzzy system for high-dimensional online possibilistic fuzzy clustering, in Proceedings of the XI-th International Scientific and Technical Conference “Computer Science and Information Technologies” (CSIT 2016) (2016), pp. 119–122. https://doi.org/10.1109/stc-csit.2016.7589884
P. Angelov, D. Filev, N. Kasabov, Evolving Intelligent Systems: Methodology and Applications (Willey, 2010)
Y.V. Bodyanskiy, O.A. Vynokurova, A.I. Dolotov, Self-learning cascade spiking neural network for fuzzy clustering based on group method of data handling. J. Autom. Inform. Sci. 45(3), 23–33 (2013)
Y. Bodyanskiy, O. Vynokurova, A. Dolotov, O. Kharchenko, Wavelet-neuro-fuzzy network structure optimization using GMDH for the solving forecasting tasks, in Proceedings of the 4th International Conference on Inductive Modelling ICIM 2013, Kyiv (2013), pp. 61–67
Y. Bodyanskiy, O. Vynokurova, N. Teslenko, Cascade GMDH-wavelet-neuro-fuzzy network, in Proceedings of the 4th International Workshop on Inductive Modeling «IWIM 2011» , Kyiv, Ukraine (2011), pp. 22–30
Y. Bodyanskiy, Y. Zaychenko, E. Pavlikovskaya, M. Samarina, Y. Viktorov, The neo-fuzzy neural network structure optimization using the GMDH for the solving forecasting and classification problems, in Proceedings of the International Workshop on Inductive Modeling, Krynica, Poland (2009), pp. 77–89
A.G. Ivakhnenko, Heuristic self-organization in problems of engineering cybernetics. Automatica 6(2), 207–219 (1970)
T. Yamakawa, E. Uchino, T. Miki, H. Kusanagi, A neo fuzzy neuron and its applications to system identification and prediction of the system behavior, in Proceedings of the 2nd International Conference on Fuzzy Logic and Neural Networks (1992), pp. 477–483
E. Uchino, T. Yamakawa, Soft computing based signal prediction, restoration and filtering, in Intelligent Hybrid Systems: Fuzzy Logic, Neural Networks and Genetic Algorithms (Kluwer Academic Publisher, Boston, 1997), pp. 331–349
T. Miki, T. Yamakawa, Analog implementation of neo-fuzzy neuron and its on-board learning, in Computational Intelligence and Applications (WSES Press, Piraeus, 1999), pp. 144–149
M. Sugeno, G.T. Kang, Structure identification of fuzzy model. Fuzzy Sets Syst. 28, 15–33 (1998)
T. Takagi, M. Sugeno, Fuzzy identification of systems and its applications to modeling and control. IEEE Trans. Syst. Man Cybern. 15, 116–132 (1985)
N. Kasabov, Evolving Connectionist Systems (Springer, London, 2003)
E. Lughofer, Evolving Fuzzy Systems—Methodologies, Advanced Concepts and Applications (Springer, Berlin, 2011)
R.J.-S. Jang, ANFIS: adaptive-network-based fuzzy inference systems. IEEE Trans. Syst. Man Cybern. 23, 665–685 (1993)
R.J.-S. Jang, C.-T. Sun, E. Mizutani, Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence (Prentice Hall, Upper Saddle River, 1997)
S. Osowski, Sieci neuronowe do przetwarzania informacji (Oficyna Wydawnicza Politechniki Warszawskiej, Warszawa, 2006)
A.G. Ivakhnenko, Long-Term Forecasting and Control of Complex Systems (Technica, Kiev, 1975)
A.G. Ivakhnenko, Polynomial theory of complex systems. IEEE Trans. Syst. Man. Cybern. 1(4), 364–378 (1971)
A.G. Ivakhnenko, Self-Learning Systems of Recognition and Automatic Control (Technica, Kiev, 1969)
A.G. Ivakhnenko, D. Wuensch, G.A. Ivakhnenko, Inductive sorting-out GMDH algorithms with polynomial complexity for active neurons of neural networks. Neural Netw. 2, 1169–1173 (1999)
A.G. Ivakhnenko, G.A. Ivakhnenko, J.A. Mueller, Self-organization of the neural networks with active neurons. Pattern Recognit. Image Anal. 4(2), 177–188 (1994)
G.A. Ivakhnenko, Self-organization of neuronet with active neurons for effects of nuclear test explosions forecasting. Syst. Anal. Model. Simul. 20, 107–116 (1995)
K.S. Narendra, K. Parthasarathy, Identification and control of dynamical systems using neural networks. IEEE Trans. Neural Netw. 1, 4–26 (1990)
T. Kondo, Identification of radial basis function networks by using revised GMDH-type neural networks with a feedback loop, in Proceedings of the SICE Annual Conference, Tokyo, Japan (2002), pp. 2882–2887
T. Ohtani, Automatic variable selection in RBF network and its application to neurofuzzy GMDH, in Proceedings of the Fourth International Conference on Knowledge-Based Intelligent Engineering Systems and Allied Technologies, vol. 2 (2000), pp. 840–843
Yu. Zaychenko, The fuzzy group method of data handling and its application for economical processes forecasting. Sci. Inq. 7(1), 83–96 (2006)
T. Ohtani, H. Ichihashi, T. Miyoshi, K. Nagasaka, Y. Kanaumi, Structural learning of neurofuzzy GMDH with Minkowski norm, in Proceedings of the 1998 Second International Conference on Knowledge-Based Intelligent Electronic Systems, vol. 2 (1998), pp. 100–107
Y. Bodyanskiy, O. Vynokurova, I. Pliss, Hybrid GMDH-neural network of computational intelligence, in Proceedings of the 3rd International Workshop on Inductive Modeling, Krynica, Poland (2009), pp. 100–107
A.G. Ivakhnenko, V.S. Stepashko, Disturbance Tolerance of Modeling (Naukova Dumka, Kiev, 1985)
Y. Bodyanskiy, N. Teslenko, P. Grimm, Hybrid evolving neural network using kernel activation functions, in Proceedings 17th Zittau East-West Fuzzy Colloquium, Zittau/Goerlitz, HS (2010), pp. 39–46
D.T. Pham, X. Liu, Neural Networks for Identification, Prediction and Control (Springer, London, 1995)
A. Bifet, Adaptive Stream Mining: Pattern Learning and Mining from Evolving Data Streams (IOS Press, Amsterdam, 2010)
C.C. Aggarwal, Data Streams: Models and Algorithms (Advances in Database Systems) (Springer, New York, 2007)
Y. Bodyanskiy, O. Tyshchenko, D. Kopaliani, An extended neo-fuzzy neuron and its adaptive learning algorithm. Int. J. Intell. Syst. Appl. (IJISA) 7(2), 21–26 (2015)
L.-X. Wang, Adaptive Fuzzy Systems and Control. Design and Statistical Analysis (Prentice Hall, Upper Saddle River, 1994)
L.-X. Wang, J.M. Mendel, Fuzzy basis functions, universal approximation, and orthogonal least-squares learning. IEEE Trans. Neural Netw. 3(5), 807–814 (1992)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Zgurovsky, M.Z., Zaychenko, Y.P. (2020). Deep Neural Networks and Hybrid GMDH-Neuro-fuzzy Networks in Big Data Analysis. In: Big Data: Conceptual Analysis and Applications. Studies in Big Data, vol 58. Springer, Cham. https://doi.org/10.1007/978-3-030-14298-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-14298-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-14297-1
Online ISBN: 978-3-030-14298-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)