Dynamic Pattern Recognition through Bio-inspired Oscillatory CNNs

Many studies in neuroscience have shown that nonlinear dynamic networks represent a bio-inspired models for information and image processing. Recent studies on the thalamo-cortical system have shown that weakly connected oscillatory networks have the capability of modelling the architecture of a neurocomputer. In particular they have associative properties and can be exploited for dynamic pattern recognition. In this manuscript the global dynamic behavior of weakly connected cellular networks of oscillators is investigated. It is assumed that each cell admits of a Lur’e description. In case of weak coupling the main dynamic features of the network are revealed by the phase deviation equation (i.e. the equation that describes the phase deviation due to the weak coupling). Firstly a very accurate analytic expression of the phase deviation equation is derived, via the joint application of the describing function technique and of Malkin’s Theorem. Then it is shown that the total number of periodic limit cycles, with their stability properties, can be estimated through the analysis of the phase deviation equation.

[1]  Leon O. Chua,et al.  The CNN paradigm , 1993 .

[2]  Peter König,et al.  Binding by temporal structure in multiple feature domains of an oscillatory neuronal network , 1994, Biological Cybernetics.

[3]  Leon O. Chua,et al.  Cellular Neural Networks and Visual Computing , 2002 .

[4]  E. Izhikevich,et al.  Weakly connected neural networks , 1997 .

[5]  A. Michel Dynamics of feedback systems , 1984, Proceedings of the IEEE.

[6]  Fernando Corinto,et al.  Periodic oscillations and bifurcations in cellular nonlinear networks , 2004, IEEE Transactions on Circuits and Systems I: Regular Papers.

[7]  Alberto Tesi,et al.  Distortion control of Chaotic Systems: the Chua's Circuit , 1993, Chua's Circuit.

[8]  E. Izhikevich,et al.  Oscillatory Neurocomputers with Dynamic Connectivity , 1999 .

[9]  A. Treisman The binding problem , 1996, Current Opinion in Neurobiology.

[10]  Yoshiki Kuramoto,et al.  Chemical Oscillations, Waves, and Turbulence , 1984, Springer Series in Synergetics.

[11]  Marco Gilli,et al.  Analysis of periodic oscillations in finite-dimensional CNNs through a spatio-temporal harmonic balance technique , 1997, Int. J. Circuit Theory Appl..

[12]  Fernando Corinto,et al.  On Global Dynamic Behavior of Weakly Connected Oscillatory Networks , 2005, Int. J. Bifurc. Chaos.

[13]  Fernando Corinto,et al.  Periodic oscillations in weakly connected cellular nonlinear networks , 2008, Proceedings. 2005 International Conference Physics and Control, 2005..