Chinese Character Learning by Synchronization in Wilson-Cowan Oscillatory Neural Networks

The cognition and learning of Chinese characters is a good example of human visual perception and learning. The synchronization behavior between neuronal groups in cortical areas is one of the core mechanisms in visual image perception and recognition. We built a neural network with locally coupled Wilson-Cowan oscillators to learn Chinese characters. Neurons in each group representing the same feature of a character will be synchronized so that the common features of Chinese characters will be extracted by the network,such as a common character in two-character words or a common radical component of characters. Further more, each feature is represented by a stable fixed point attractor in the dynamic neural network.

[1]  J. Cowan,et al.  Excitatory and inhibitory interactions in localized populations of model neurons. , 1972, Biophysical journal.

[2]  M. Grattarola,et al.  Necessary and sufficient conditions for synchronization of nonlinear oscillators with a given class of coupling , 1977 .

[3]  Mark S. Seidenberg,et al.  Phonology, reading acquisition, and dyslexia: insights from connectionist models. , 1999 .

[4]  DeLiang Wang,et al.  Synchronization and desynchronization in a network of locally coupled Wilson-Cowan oscillators , 1996, IEEE Trans. Neural Networks.

[5]  M. Alexander,et al.  Principles of Neural Science , 1981 .

[6]  Nancy Kopell,et al.  Rapid synchronization through fast threshold modulation , 1993, Biological Cybernetics.

[7]  I. Biederman,et al.  Dynamic binding in a neural network for shape recognition. , 1992, Psychological review.

[8]  Trevor Darrell,et al.  Visual speech recognition with loosely synchronized feature streams , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[9]  Joachim M. Buhmann,et al.  Sensory segmentation with coupled neural oscillators , 1992, Biological Cybernetics.

[10]  Mark S. Seidenberg,et al.  Phonology, reading acquisition, and dyslexia: insights from connectionist models. , 1999, Psychological review.

[11]  W. Singer,et al.  Synchronization of oscillatory responses in visual cortex correlates with perception in interocular rivalry. , 1997, Proceedings of the National Academy of Sciences of the United States of America.

[12]  S. Bressler.  Interareal synchronization in the visual cortex , 1996, Behavioural Brain Research.

[13]  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.

[14]  Guanrong Chen,et al.  On Synchronization and Control of Coupled Wilson-cowan Neural oscillators , 2003, Int. J. Bifurc. Chaos.

[15]  Ch. von der Malsburg,et al.  A neural cocktail-party processor , 1986, Biological Cybernetics.

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

[17]  Leslie S. Smith,et al.  Constraints on Synchronizing Oscillator Networks , 1993, Neural Computation.

[18]  J P Changeux,et al.  Chemical signaling in the brain. , 1993, Scientific American.

[19]  J. Fischer.  Principles of Neural Science (3rd ed.) , 1993 .

[20]  F. Bloom.  Principles of Neural Science, 3rd ed , 1993 .

[21]  Roman Borisyuk,et al.  Analysis of Oscillatory Regimes of a Coupled Neural Oscillator System with Application to Visual Cortex Modeling , 1992 .