NNs Recognize Chaotic Attractors

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.

[1]  Ryotaro Kamimura,et al.  Similarity interaction in information-theoretic self-organizing maps , 2013, Int. J. Gen. Syst..

[2]  C. Lee Giles,et al.  Learning Chaotic Attractors by Neural Networks , 2000, Neural Computation.

[3]  Katsunari Shibata,et al.  Effect of number of hidden neurons on learning in large-scale layered neural networks , 2009, 2009 ICCAS-SICE.

[4]  N. Rambidi,et al.  Neural network devices based on reaction–duffusion media: an approach to artificial retina , 1998 .

[5]  A. Loaiza-Brito,et al.  Foveal model of artificial retina with phototransistors in Darlington configuration in the high-resolution region , 2005, 2005 2nd International Conference on Electrical and Electronics Engineering.

[6]  Eduardo García-Breijo,et al.  A comparison study of pattern recognition algorithms implemented on a microcontroller for use in an electronic tongue for monitoring drinking waters , 2011 .

[7]  Horia-Nicolai Teodorescu,et al.  Modeling natural sensitivity : ALife sensitive, selective sensors , 2000 .

[8]  Jang-Kyoo Shin,et al.  An Artificial Retina Chip Using Switch-Selective Resistive Network for Intelligent Sensor Systems , 2006, ICIC.

[9]  Shamsuddin Ahmed.  Performance of a coordinate search ANN training algorithm , 2013, Int. J. Gen. Syst..

[10]  Michael P. Craven,et al.  The prediction of bacteria type and culture growth phase by an electronic nose with a multi-layer pe , 1998 .

[11]  R. J. Fogler,et al.  An artificial retina for SAR object recognition , 1996, Proceeding of Southwest Symposium on Image Analysis and Interpretation.

[12]  Guang-Bin Huang,et al.  Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions , 1998, IEEE Trans. Neural Networks.

[13]  Horia-Nicolai L. Teodorescu,et al.  Classifiers for decoding patterns in the response of an artificial retina , 2013, International Symposium on Signals, Circuits and Systems ISSCS2013.

[14]  Julien Clinton Sprott,et al.  A new class of chaotic circuit , 2000 .

[15]  Horia-Nicolai L. Teodorescu,et al.  Optical sensors based on chaotic systems , 2012, 2012 16th International Conference on System Theory, Control and Computing (ICSTCC).

[16]  José Manuel Ferrández,et al.  Artificial Neural Networks and Retinal Ganglion Cell Responses , 2011 .

[17]  Francis Devos,et al.  A programmable artificial retina , 1993 .

[18]  J. Ohta,et al.  An artificial retina chip with current-mode focal plane image processing functions , 1997 .

[19]  Horia-Nicolai Teodorescu,et al.  Intelligent Sensor, Monitoring and Control Systems Based on Nonlinear Dynamics for Space Environments , 2005 .

[20]  Javier Díaz,et al.  Visual System Based on Artificial Retina for Motion Detection , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[21]  S. Romero,et al.  Cortical visual neuro-prosthesis for the blind: retina-like software/hardware preprocessor , 2003, First International IEEE EMBS Conference on Neural Engineering, 2003. Conference Proceedings..

[22]  Raúl Rojas,et al.  The Backpropagation Algorithm , 1996 .

[23]  Abraham Kandel,et al.  Nonlinear Dynamics Sensitivity Analysis in Networks and Applications to Sensing 1 , 2001 .

[24]  Antonio Martínez-Álvarez,et al.  A design framework to model retinas , 2007, Biosyst..

[25]  Kazuo Kyuma,et al.  Artificial retina chips as on-chip image processors and gesture-oriented interfaces , 1999 .

[26]  M. Sugisaka,et al.  Developing an artificial retina by evolutionary cellular automata and self-organizing neural networks , 2006, Artificial Life and Robotics.

[27]  Yih-Fang Huang,et al.  Bounds on the number of hidden neurons in multilayer perceptrons , 1991, IEEE Trans. Neural Networks.

[28]  Terry L. Kastens,et al.  Feedforward Backpropagation Neural Networks in Prediction of Farmer Risk Preferences , 1996 .

[29]  Guang Li,et al.  Application of Chaotic Neural Model Based on Olfactory System on Pattern Recognitions , 2005, ICNC.

[30]  Thierry M. Bernard,et al.  Second generation programmable artificial retina , 1999, Twelfth Annual IEEE International ASIC/SOC Conference (Cat. No.99TH8454).

[31]  Horia-Nicolai L. Teodorescu,et al.  Characterization of nonlinear dynamic systems for engineering purposes – a partial review , 2012, Int. J. Gen. Syst..