NNs Recognize Chaotic Attractors
Horia-Nicolai Teodorescu, Mircea Gh. Hulea · 2013
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.