Neuro-Fuzzy Kolmogorov's Network for Time Series Prediction and Pattern Classification

In the paper, a novel Neuro-Fuzzy Kolmogorov's Network (NFKN) is considered. The NFKN is based on and is the development of the previously proposed neural and fuzzy systems using the famous Kolmogorov's superposition theorem (KST). The network consists of two layers of neo-fuzzy neurons (NFNs) and is linear in both the hidden and output layer parameters, so it can be trained with very fast and simple procedures: the gradient-descent based learning rule for the hidden layer, and the recursive least squares algorithm for the output layer. The validity of theoretical results and the advantages of the NFKN are confirmed by experiments.

[1]  Bart Kosko,et al.  Fuzzy Systems as Universal Approximators , 1994, IEEE Trans. Computers.

[2]  Boris Igelnik,et al.  Kolmogorov's spline network , 2003, IEEE Trans. Neural Networks.

[3]  David A. Sprecher,et al.  A Numerical Implementation of Kolmogorov's Superpositions II , 1996, Neural Networks.

[4]  Rudolf Kruse,et al.  Generating classification rules with the neuro-fuzzy system NEFCLASS , 1996, Proceedings of North American Fuzzy Information Processing.

[5]  Chuen-Tsai Sun,et al.  A neuro-fuzzy classifier and its applications , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[6]  Yevgeniy Bodyanskiy,et al.  Neuro-fuzzy Kolmogorov's Network , 2005, ICANN.

[7]  L. Glass,et al.  Oscillation and chaos in physiological control systems. , 1977, Science.

[8]  Vra Krkov.  Kolmogorov's Theorem Is Relevant , 1991, Neural Computation.

[9]  Lakhmi C. Jain,et al.  Knowledge-Based Intelligent Information and Engineering Systems , 2004, Lecture Notes in Computer Science.

[10]  Yevgeniy V. Bodyanskiy,et al.  Fuzzy Kolmogorov's Network , 2004, KES.

[11]  Yevgeniy V. Bodyanskiy,et al.  Universal Approximator Employing Neo-Fuzzy Neurons , 2004, Fuzzy Days.

[12]  Chuen-Tsai Sun,et al.  Adaptive Network Based Fuzzy Classification , 1992 .

[13]  Yeung Yam,et al.  Multi-resolution techniques in the rules-based intelligent control systems: a universal approximation result , 1999, Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014).