Kohonen Neural Networks and Language

Kohonen neural networks are a type of self-organizing network that recognizes the statistical characteristics of input datasets. The application of this type of neural network to language theory is demonstrated in the present note by showing three brief applications: recognizing word borders, learning the limited phonemes of one's native tongue, and category-specific naming impairments.

[1]  Noam Chomsky,et al.  वाक्यविन्यास का सैद्धान्तिक पक्ष = Aspects of the theory of syntax , 1965 .

[2]  R. Berndt,et al.  Category-specific naming deficit following cerebral infarction , 1985, Nature.

[3]  G. Edelman,et al.  The NO hypothesis: possible effects of a short-lived, rapidly diffusible signal in the development and function of the nervous system. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[4]  A. Caramazza,et al.  Category-specific naming and comprehension impairment: a double dissociation. , 1991, Brain : a journal of neurology.

[5]  Martha J. Farah,et al.  Semantically-bounded anomia: Implications for the neural implementation of naming , 1992, Neuropsychologia.

[6]  K. Stevens,et al.  Linguistic experience alters phonetic perception in infants by 6 months of age. , 1992, Science.

[7]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[8]  Helge Ritter,et al.  Self-organizing feature maps: Kohonen maps , 1998 .

[9]  R N Aslin,et al.  Statistical Learning by 8-Month-Old Infants , 1996, Science.

[10]  H. Markram,et al.  Regulation of Synaptic Efficacy by Coincidence of Postsynaptic APs and EPSPs , 1997, Science.

[11]  D. Johnston,et al.  A Synaptically Controlled, Associative Signal for Hebbian Plasticity in Hippocampal Neurons , 1997, Science.

[12]  James A. Anderson,et al.  An Introduction To Neural Networks , 1998 .