Learning algorithm of the revised RBF network and its application to the media art system

Authors:
Chihiro Kondo;Tadashi Kondo
Affiliations:
Graduate School of Media Design, Keio University, Yokohama, Japan;Graduate School of Health Sciences, University of Tokushima, Tokushima, Japan 770-8509
Venue:
Artificial Life and Robotics
Year:
2010

Citing 3
Cited 0

Processing: A Programming Handbook for Visual Designers and Artists

Processing: A Programming Handbook for Visual Designers and Artists
Fast learning in networks of locally-tuned processing units

Neural Computation
GMDH-type neural network algorithm with a feedback loop for structural identification of RBF neural network

International Journal of Knowledge-based and Intelligent Engineering Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this study, a revised radial basis function (RBF) network is proposed and applied to the identification problems of a nonlinear system and a media art system. In the revised RBF network, the structural parameters such as the means and variances of the radial basis functions in the neurons are determined automatically, and so the revised RBF network can easily be applied to practical complex problems such as the media art system. The media art system outputs art expressions such as sound and graphics using the artificial sensibility surfaces that are identified using the revised RBF network.