Neuro-Fuzzy kolmogorov's network for time series prediction and pattern classification

Authors:
Yevgeniy Bodyanskiy;Vitaliy Kolodyazhniy;Peter Otto
Affiliations:
Control Systems Research Laboratory, Kharkiv National University of Radioelectronics, Kharkiv, Ukraine;Control Systems Research Laboratory, Kharkiv National University of Radioelectronics, Kharkiv, Ukraine;Department of Informatics and Automation, Technical University of Ilmenau, Ilmenau, Germany
Venue:
KI'05 Proceedings of the 28th annual German conference on Advances in Artificial Intelligence
Year:
2005

Citing 5
Cited 0

A numerical implementation of Kolmogorov's superpositions

Neural Networks
A numerical implementation of Komogorov's superpositions II

Neural Networks
Kolmogorov's theorem is relevant

Neural Computation
Neuro-fuzzy Kolmogorov's network

ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
Kolmogorov's spline network

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.