Function Decomposition Network

Authors:
Yevgeniy Bodyanskiy;Sergiy Popov;Mykola Titov
Affiliations:
Control Systems Research Laboratory, Kharkiv National University of Radio Electronics,;Control Systems Research Laboratory, Kharkiv National University of Radio Electronics,;Control Systems Research Laboratory, Kharkiv National University of Radio Electronics,
Venue:
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Year:
2009

Citing 12
Cited 0

Kolmogorov's theorem and multilayer neural networks

Neural Networks
Computational aspects of Kolmogorov's superposition theorem

Neural Networks
Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence

Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Second-Order Methods for Neural Networks

Second-Order Methods for Neural Networks
Neural Networks for Identification, Prediction, and Control

Neural Networks for Identification, Prediction, and Control
Space-filling curves and Kolmogorov superposition-based neural networks

Neural Networks
Constructing Intermediate Concepts by Decomposition of Real Functions

ECML '97 Proceedings of the 9th European Conference on Machine Learning
Function Decomposition in Machine Learning

Machine Learning and Its Applications, Advanced Lectures
Kolmogorov's theorem is relevant

Neural Computation
Representation properties of networks: Kolmogorov's theorem is irrelevant

Neural Computation
Kolmogorov's spline network

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Novel neural network architecture is proposed to solve the nonlinear function decomposition problem. Top-down approach is applied that does not require prior knowledge about the function's properties. Abilities of our method are demonstrated using synthetic test functions and confirmed by a real-world problem solution. Possible directions for further development of the presented approach are discussed.