Perceptual grouping through competition in coupled oscillator networks

Abstract In this paper we present a novel approach to model perceptual grouping based on phase and frequency synchronization in a network of coupled Kuramoto oscillators. Transferring the grouping concept from the Competitive Layer Model (CLM) to a network of Kuramoto oscillators, we preserve the excellent grouping capabilities of the CLM, while dramatically improving the convergence rate, robustness to noise, and computational performance, which is verified in a series of artificial grouping experiments and with real-world data.

[1]  Tomoko Yoshikawa,et al.  Circadian Organization Is Governed by Extra-SCN Pacemakers , 2010, Journal of biological rhythms.

[2]  S. Strogatz.  From Kuramoto to Crawford: exploring the onset of synchronization in populations of coupled oscillators , 2000 .

[3]  Heiko Wersing.  Spatial feature binding and learning in competitive neural layer architectures , 2000 .

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

[5]  Fabricio A. Breve,et al.  Chaotic phase synchronization and desynchronization in an oscillator network for object selection , 2009, Neural Networks.

[6]  Guy J. Brown,et al.  A neural oscillator sound separator for missing data speech recognition , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[7]  Helge Ritter,et al.  A Spatial Approach to Feature Linking , 1990 .

[8]  Deliang Wang,et al.  Global competition and local cooperation in a network of neural oscillators , 1995 .

[9]  Heiko Wersing,et al.  A neural network architecture for automatic segmentation of fluorescence micrographs , 2002, ESANN.

[10]  A. Arenas,et al.  Synchronization processes in complex networks , 2006, nlin/0610057.

[11]  Chunguang Li,et al.  Fast and robust image segmentation by small-world neural oscillator networks , 2011, Cognitive Neurodynamics.

[12]  R. Sepulchre,et al.  Oscillator Models and Collective Motion , 2007, IEEE Control Systems.

[13]  Mason A. Porter,et al.  Robust Detection of Dynamic Community Structure in Networks , 2012, Chaos.

[14]  Hyunsuk Hong,et al.  Kuramoto model of coupled oscillators with positive and negative coupling parameters: an example of conformist and contrarian oscillators. , 2011, Physical review letters.

[15]  Heiko Wersing,et al.  A computational feature binding model of human texture perception , 2004, Cognitive Processing.

[16]  Helge J. Ritter,et al.  Neural competition for motion segmentation , 2010, ESANN.

[17]  Heiko Wersing.  Learning Lateral Interactions for Feature Binding and Sensory Segmentation , 2001, NIPS.

[18]  Jean-Jacques E. Slotine,et al.  Visual Grouping by Neural Oscillator Networks , 2009, IEEE Transactions on Neural Networks.

[19]  Roseli A. Francelin Romero,et al.  Selecting salient objects in real scenes: An oscillatory correlation model , 2011, Neural Networks.

[20]  M. Spong,et al.  On Synchronization of Kuramoto Oscillators , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[21]  B. S. Manjunath,et al.  Texture Features for Browsing and Retrieval of Image Data , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Per Sebastian Skardal,et al.  Hierarchical synchrony of phase oscillators in modular networks. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.