Recognizing Fractal Patterns Using a Ring of Phase Oscillators

A ring of phase oscillators has been proved to be useful for pattern recognition. It has at least three nontrivial advantages over the traditional dynamical neural networks, such as Hopfield Model: First, each input pattern can be encoded in a vector instead of a matrix, second, the connection weights can be determined analytically, third, due to its dynamical nature, it has the ability to capture temporal patterns. In the previous studies of this topic, all patterns are encoded as stable periodic solutions of the oscillator network. In this paper, we continue to explore the oscillator ring for pattern recognition. Specifically, we propose algorithms, which use the chaotic dynamics of the closed loops of Stuart-Landau Oscillators as artificial neurons, to recognize randomly generated fractal patterns. It is worth to note that fractal pattern recognition is a challenge problem due to their discontinuity nature and their complex form.

[1]  Wulfram Gerstner,et al.  A neuronal learning rule for sub-millisecond temporal coding , 1996, Nature.

[2]  Liang Zhao,et al.  Chaotic dynamics for multi-value content addressable memory , 2006, Neurocomputing.

[3]  Walter J. Jermakowicz,et al.  Neural networks a century after Cajal , 2007, Brain Research Reviews.

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

[5]  Stephen Grossberg,et al.  Competitive Learning: From Interactive Activation to Adaptive Resonance , 1987, Cogn. Sci..

[6]  Christoph von der Malsburg,et al.  The Correlation Theory of Brain Function , 1994 .

[7]  Matthias Wolfrum,et al.  Destabilization patterns in chains of coupled oscillators. , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.

[8]  G. Deco,et al.  Emerging concepts for the dynamical organization of resting-state activity in the brain , 2010, Nature Reviews Neuroscience.

[9]  I Fischer,et al.  Amplitude and phase effects on the synchronization of delay-coupled oscillators. , 2010, Chaos.

[10]  M. V. Velzen,et al.  Self-organizing maps , 2007 .

[11]  David Kleinfeld,et al.  Closed-loop neuronal computations: focus on vibrissa somatosensation in rat. , 2003, Cerebral cortex.

[12]  Peter A Tass,et al.  Delay- and coupling-induced firing patterns in oscillatory neural loops. , 2011, Physical review letters.

[13]  W. Pan,et al.  Synchronization preservability of intermittent coupling chaotic semiconductor lasers , 2011 .

[14]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[15]  Yoko Yamaguchi,et al.  A theory of hippocampal memory based on theta phase precession , 2003, Biological Cybernetics.

[16]  S Yanchuk,et al.  Periodic patterns in a ring of delay-coupled oscillators. , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[17]  Liang Zhao,et al.  Network-Based High Level Data Classification , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Roman Borisyuk,et al.  Spiking neural network model for memorizing sequences with forward and backward recall , 2013, Biosyst..

[19]  D. Wang,et al.  The time dimension for scene analysis , 2005, IEEE Transactions on Neural Networks.