Title :
NNs Recognize Chaotic Attractors
Author :
Teodorescu, Horia-Nicolai L. ; Hulea, Mircea Gh
Author_Institution :
Dept. Electron., Telecommun. & Inf. Technol., Tech. Univ. Gheorghe Asachi of Iasi, Iasi, Romania
Abstract :
We demonstrate that visual (geometric) patterns can be robustly recognized by an artificial retina composed of a chaotic sensitive system where the coding of the patterns is by attractor features and an artificial neural network is used to classify the attractors. This opens the door to sensorial systems that mimic the biological ones. The specificity of solutions of chaotic systems to their parameters and the universal approximation capability of ANNs form the theoretical foundations of this research. This paper is a preliminary publication.
Keywords :
approximation theory; chaos; electronic engineering computing; neural nets; pattern recognition; ANN approximation capability; artificial neural network; attractor feature; biological system; chaotic attractor recognition; chaotic sensitive system; pattern coding; sensorial system; visual pattern; Artificial neural networks; Biological neural networks; Chaos; Neurons; Pattern recognition; Training; Visualization; chaotic circuit; multilayer perceptron; visual pattern recognition;
Conference_Titel :
Control Systems and Computer Science (CSCS), 2013 19th International Conference on
Conference_Location :
Bucharest
Print_ISBN :
978-1-4673-6140-8
DOI :
10.1109/CSCS.2013.7
