ON-LINE NEO-PHASE AUTOENKODER FOR SYSTEMS WITH DEEP LEARNING ON THE BASE OF THE KOLMOGOROV’S NEURO-PHASE NETWORK
Keywords:
Neo-fuzzy autoencoder, deep learning neural network, Kolmogorov’s neuro-fuzzy network, data reduction-compression, machine lear-ning
Abstract
One of the important problem, which is connected with big high dimensional data processing, is the task of their compression without significant loss of information that is contained in this data. The systems, which solve this problem and are called autoencoders, are the inherent part of deep neural networks. The main disadvantage of well-known autoencoders is low speed of learning process, which is implemented in the batch mode. In the paper the two-layered autoencoder is proposed. This system is the modification of Kolmogorov’s neuro-fuzzy system. Thus, in the paper the hybrid neo-fuzzy syste- mencoder is proposed that has essentially advantages comparatively with conventional neurocompressors-encoders.
Downloads
Download data is not yet available.
References
1. Han J. Data Mining: Concepts and Techniques / J. Han, M. Kamber. – Amsterdam: Morgan Kaufman Publ. – 2006. – 743 p.
2. Aggarwal C.C. Data Mining / C.C. Aggarwal. – N.Y.: Springer, 2015. – 734 p.
3. Cichocki А. Neural Networks for Optimization and Signal Proces-sing / А. Cichocki, R. Unbehauen. – Stuttgart: Teubner, 1993. – 526 р.
4. Haykin S. Neural Networks and Learning Machines / S. Haykin. – Upper Saddle River. − New Jersey: Pearson, Prentice Hall, 2009. – 906 p.
5. LeCun Y. Deep Learning / Y. LeCun, Y. Bengio, G.E. Hinton // Nature. – 2015. – 521. – P. 436-444.
6. Schmidhuber J. Deep learning in neural networks: An overview / J. Schmidhuber // Neural Networks. – 2015. – 61. – P. 85-117.
7. Goodfellow I. Deep learning / I. Goodfellow, Y. Bengio, A. Courville. − MIT Press. – 2016. – 800 p.
8. Bifet A. Adaptive Stream Mining: Pattern Learning and Mining from Evolving Data Streams / A. Bifet. – Amsterdam: IOS Press, 2010. – 224 p.
9. Aggarwal C.C. Data Streams: Models and Algorithms / C.C. Aggarwal. − Kluwer Academic Publishers Boston/Dordrecht/London. – 2007. – 354 p.
10. Kolodyazhniy V. Fuzzy Kolmogorov’s Network / V. Kolodyazhniy, Ye. Bodyanskiy // In M.G. Negoita et al., editors, Lecture Notes in Computer Science. – V. 3214. – Springer-Verlag. – 2004. – P. 764-771.
11. Bodyanskiy Ye. Neuro-fuzzy Kolmogorov’s network for time-series prediction and pattern classification / Ye. Bodyanskiy, V. Kolodyazhniy, P. Otto // Lecture Notes in Artificial Intelligence. – V. 3698. – Heidelberg: Springer –Verlag. – 2005. – P. 191-202.
12. Kolodyazhniy V. Universal approximator employing neo-fuzzy neurons / Ye. Bodyanskiy, V. Kolodyazhniy, P. Otto // Ed. B. Reusch «Computational Intelligence Theory and Applications». – Berlin-Heidelberg: Springer, 2005. – P. 631-640.
13. Kolodyazhniy V. Neuro-fuzzy Kolmogorov’s network with a modified perceptron learning rule for classification problems / V. Kolodyazhniy, Ye. Bodyanskiy, V. Poyedyntseva, A. Stephan // Ed. B. Reuch «Advances in Soft Computing». – V. 38. – Berlin-Heidelberg: Springer-Verlag. – 2006. – P.41-49.
14. Bodyanskiy Ye. Neuro-fuzzy Kolmogorov's network / Ye. Bodyanskiy, Ye. Gorshkov, V. Kolodyazhniy, V. Poyedyntseva // Lecture Notes in Computer Science. – V.3697. – Berlin-Heidelberg: Springer-Verlag, 2005. – P.1-6.
15. Yamakawa T. A novel nonlinear synapse neuron model guaranteeing a global minimum – Wavelet neuron / T. Yamakawa // Proc. 28-th IEEE Int. Symp. on Multiple-Valued Logic. −Fukuoka. Japan: IEEE Comp. Soc. – 1998. – P. 335-336.
16. Uchino E. Soft computing based signal prediction, restoration and filtering / E. Uchino, T. Yamakawa // Intelligent Hybrid Systems: Fuzzy Logic, Neural Networks and Genetic Algorithms, Da Ruan Eds.− Boston: Kluwer Academic Publisher. – 1997. – P. 331-349.
17. Yamakawa T. A neo-fuzzy neuron and its applications to system identification and prediction of the system behavior / T. Yamakawa, E. Uchino, T. Miki, H. Kusanagi // Proc. 2-nd Int. Conf. on Fuzzy Logic and Neural Networks «IIZUKA-92». −Iizuka, Japan. – 1992. – P. 477-483.
18. Jang J.-S. R. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence / J.-S. R. Jang, C. T. Sun, E. Mizutani. – N.J.: Prentice Hall, 1997. – 614 p.
19. Yam Y. Multi-resolution techniques in the rules-based intelligent control systems: a universal approximation result / Y. Yam, H.T. Nguyen, V. Kreinovich // Proc. of the 14th IEEE International Symposium on Intelligent Control/Intelligent Systems and Semio-tics (ISIC/ISAS'99). − Cambridge, Massachusetts, September. − 15-17. – 1999. – P. 213-218.
2. Aggarwal C.C. Data Mining / C.C. Aggarwal. – N.Y.: Springer, 2015. – 734 p.
3. Cichocki А. Neural Networks for Optimization and Signal Proces-sing / А. Cichocki, R. Unbehauen. – Stuttgart: Teubner, 1993. – 526 р.
4. Haykin S. Neural Networks and Learning Machines / S. Haykin. – Upper Saddle River. − New Jersey: Pearson, Prentice Hall, 2009. – 906 p.
5. LeCun Y. Deep Learning / Y. LeCun, Y. Bengio, G.E. Hinton // Nature. – 2015. – 521. – P. 436-444.
6. Schmidhuber J. Deep learning in neural networks: An overview / J. Schmidhuber // Neural Networks. – 2015. – 61. – P. 85-117.
7. Goodfellow I. Deep learning / I. Goodfellow, Y. Bengio, A. Courville. − MIT Press. – 2016. – 800 p.
8. Bifet A. Adaptive Stream Mining: Pattern Learning and Mining from Evolving Data Streams / A. Bifet. – Amsterdam: IOS Press, 2010. – 224 p.
9. Aggarwal C.C. Data Streams: Models and Algorithms / C.C. Aggarwal. − Kluwer Academic Publishers Boston/Dordrecht/London. – 2007. – 354 p.
10. Kolodyazhniy V. Fuzzy Kolmogorov’s Network / V. Kolodyazhniy, Ye. Bodyanskiy // In M.G. Negoita et al., editors, Lecture Notes in Computer Science. – V. 3214. – Springer-Verlag. – 2004. – P. 764-771.
11. Bodyanskiy Ye. Neuro-fuzzy Kolmogorov’s network for time-series prediction and pattern classification / Ye. Bodyanskiy, V. Kolodyazhniy, P. Otto // Lecture Notes in Artificial Intelligence. – V. 3698. – Heidelberg: Springer –Verlag. – 2005. – P. 191-202.
12. Kolodyazhniy V. Universal approximator employing neo-fuzzy neurons / Ye. Bodyanskiy, V. Kolodyazhniy, P. Otto // Ed. B. Reusch «Computational Intelligence Theory and Applications». – Berlin-Heidelberg: Springer, 2005. – P. 631-640.
13. Kolodyazhniy V. Neuro-fuzzy Kolmogorov’s network with a modified perceptron learning rule for classification problems / V. Kolodyazhniy, Ye. Bodyanskiy, V. Poyedyntseva, A. Stephan // Ed. B. Reuch «Advances in Soft Computing». – V. 38. – Berlin-Heidelberg: Springer-Verlag. – 2006. – P.41-49.
14. Bodyanskiy Ye. Neuro-fuzzy Kolmogorov's network / Ye. Bodyanskiy, Ye. Gorshkov, V. Kolodyazhniy, V. Poyedyntseva // Lecture Notes in Computer Science. – V.3697. – Berlin-Heidelberg: Springer-Verlag, 2005. – P.1-6.
15. Yamakawa T. A novel nonlinear synapse neuron model guaranteeing a global minimum – Wavelet neuron / T. Yamakawa // Proc. 28-th IEEE Int. Symp. on Multiple-Valued Logic. −Fukuoka. Japan: IEEE Comp. Soc. – 1998. – P. 335-336.
16. Uchino E. Soft computing based signal prediction, restoration and filtering / E. Uchino, T. Yamakawa // Intelligent Hybrid Systems: Fuzzy Logic, Neural Networks and Genetic Algorithms, Da Ruan Eds.− Boston: Kluwer Academic Publisher. – 1997. – P. 331-349.
17. Yamakawa T. A neo-fuzzy neuron and its applications to system identification and prediction of the system behavior / T. Yamakawa, E. Uchino, T. Miki, H. Kusanagi // Proc. 2-nd Int. Conf. on Fuzzy Logic and Neural Networks «IIZUKA-92». −Iizuka, Japan. – 1992. – P. 477-483.
18. Jang J.-S. R. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence / J.-S. R. Jang, C. T. Sun, E. Mizutani. – N.J.: Prentice Hall, 1997. – 614 p.
19. Yam Y. Multi-resolution techniques in the rules-based intelligent control systems: a universal approximation result / Y. Yam, H.T. Nguyen, V. Kreinovich // Proc. of the 14th IEEE International Symposium on Intelligent Control/Intelligent Systems and Semio-tics (ISIC/ISAS'99). − Cambridge, Massachusetts, September. − 15-17. – 1999. – P. 213-218.
Published
2017-09-27
How to Cite
БОДЯНСЬКИЙ, Є., ВИНОКУРОВА, О., ПЕЛЕШКО, Д., & РАШКЕВИЧ, Ю. (2017). ON-LINE NEO-PHASE AUTOENKODER FOR SYSTEMS WITH DEEP LEARNING ON THE BASE OF THE KOLMOGOROV’S NEURO-PHASE NETWORK. Transport Development, (1(1), 60-67. https://doi.org/10.33082/td.2017.1-1.06
Section
INFORMATION INTELLECTUAL TECHNOLOGIES IN AUTOMATED SYSTEMS OF DATA PROCESSING AN
This work is licensed under a Creative Commons Attribution 4.0 International License.
