Two-Stage Habituation Based Neural Networks for Dynamic Signal Classification

Abstract This article describes a novel neural network structure designed for the dynamic classification of spatio-temporal signals. The network is a two-stage structure consisting of a biologically motivated temporal encoding stage followed by a static neural classifier stage. The temporal encoding stage is based upon a simple biological learning mechanism known as habituation. This habituation based neural structure is capable of approximating arbitrarily well any continuous, causal, time-invariant, mapping from one discrete time sequence to another. Such a structure is applicable to SONAR and speech signal classification problems, among others. Experiments on classification of high dimensional feature vectors obtained from Banzhaf sonograms, demonstrate that the proposed network performs better than time delay neural networks while using a substantially simpler structure.

[1]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[2]  I. W. Sandberg.  Approximately-finite memory and the theory of representations , 1992 .

[3]  Geoffrey E. Hinton,et al.  Proceedings of the 1988 Connectionist Models Summer School , 1989 .

[4]  John H. Byrne,et al.  Mathematical Model of Cellular and Molecular Processes Contributing to Associative and Nonassociative Learning in Aplysia , 1989 .

[5]  Joydeep Ghosh,et al.  Classification of Spatiotemporal Patterns with Applications to Recognition of Sonar Sequences , 1995 .

[6]  José Carlos Príncipe,et al.  The gamma model--A new neural model for temporal processing , 1992, Neural Networks.

[7]  Joydeep Ghosh,et al.  A habituation based neural network for spatio-temporal classification , 1995, Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing.

[8]  I. Sandberg,et al.  Network approximation of input-output maps and functionals , 1995, Proceedings of 1995 34th IEEE Conference on Decision and Control.

[9]  Richard Lippmann,et al.  Review of Neural Networks for Speech Recognition , 1989, Neural Computation.

[10]  C. Coen,et al.  Functions of the Brain , 1985 .

[11]  Irwin W. Sandberg.  Multidimensional nonlinear Systems and Structure Theorems , 1992, J. Circuits Syst. Comput..

[12]  Sun-Yuan Kung,et al.  Digital neural networks , 1993, Prentice Hall Information and System Sciences Series.

[13]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[14]  Tony R. Martinez,et al.  Digital Neural Networks , 1988, Proceedings of the 1988 IEEE International Conference on Systems, Man, and Cybernetics.

[15]  Joydeep Ghosh,et al.  A neural network based hybrid system for detection, characterization, and classification of short-duration oceanic signals , 1992 .

[16]  Robert F. Port,et al.  Neural Representation of Temporal Patterns , 1995, Springer US.

[17]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[18]  Irwin W. Sandberg,et al.  Structure theorems for nonlinear systems , 1991, Multidimens. Syst. Signal Process..

[19]  P J Abbas,et al.  Neural responses to auditory temporal patterns. , 1990, The Journal of the Acoustical Society of America.

[20]  Joydeep Ghosh,et al.  Habituation-based mechanism for encoding temporal information in artificial neural networks , 1995, SPIE Defense + Commercial Sensing.

[21]  G. Lynch,et al.  Derivation of Encoding Characteristics of Layer II Cerebral Cortex , 1989, Journal of Cognitive Neuroscience.

[22]  Joydeep Ghosh,et al.  A temporal memory network with state-dependent thresholds , 1993, IEEE International Conference on Neural Networks.

[23]  Structure theorems for nonlinear systems , 1992, Multidimens. Syst. Signal Process..

[24]  S Dehaene,et al.  Neural networks that learn temporal sequences by selection. , 1987, Proceedings of the National Academy of Sciences of the United States of America.

[25]  Robert M. Pap,et al.  Handbook of neural computing applications , 1990 .

[26]  P. Nicolas,et al.  Adaptive classification of underwater transients , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[27]  Irwin W. Sandberg,et al.  Network approximation of input-output maps and functionals , 1995, Proceedings of 1995 34th IEEE Conference on Decision and Control.

[28]  P.M. Djuric,et al.  Segmentation of nonstationary signals , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[29]  Judith E. Dayhoff.  Regularity properties in pulse transmission networks , 1990, 1990 IJCNN International Joint Conference on Neural Networks.