Biologically Inspired Architecture of Feedforward Networks for Signal Classification

  • Šarūnas Raudys
  • Minija Tamošiūnaitė
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1876)

Abstract

The hypothesis is that in the lowest hidden layers of biological systems “local subnetworks” are smoothing an input signal. The smoothing accuracy may serve as a feature to feed the subsequent layers of the pattern classification network. The present paper suggests a multistage supervised and “unsupervised” training approach for design and training of multilayer feed-forward networks. Following to the methodology used in the statistical pattern recognition systems we split functionally the decision making process into two stages. In an initial stage, we smooth the input signal in a number of different ways and, in the second stage, we use the smoothing accuracy as a new feature to perform a final classification.

Keywords

Hide Layer Ventricular Fibrillation Feedforward Network High Frequency Oscillation Radial Basic Function 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Atick J.J., Redlich A.N.: Towards a theory of early visual processing. Neural Computation 2 (1990) 308–320.CrossRefGoogle Scholar
  2. 2.
    Blužaitė I., Blužas, J., Brazdžionyte, J.: Signal-averaged electrocardiogram. Peculiarities of the first and recurrent Myocardial Infarction. J. HK Coll. Cardiol. 5 (1997) 119–25Google Scholar
  3. 3.
    Burattini, L., Zareba, W., Rashba, E.J. et al: ECG Features of Microvolt T-Wave Alternans in Coronary Artery Disease and Long QT Syndrome Patients. Journal of Electrocardiology, 31 (1997) 114–120CrossRefGoogle Scholar
  4. 4.
    LeCun, Y., Boser, B, Denker, J.S., Henderson, D.,. Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition, Neural Computation, 1 (1990) 541–551CrossRefGoogle Scholar
  5. 5.
    Devijver P.A., Kittler J.: Pattern Recognition. A Statistical Approach, Precentice-Hall International, Inc., London (1982)Google Scholar
  6. 6.
    Dong, D.W.: (1993) Associative deccorelation dynamics in visual cortex, Lawrence Berkeley Laboratory Technical Report, LBL-34491 (1993)Google Scholar
  7. 7.
    Dong, D.W.: Associative deccorelation dynamics: a theory of self organization and optimization in feedback networks. In: Tesauro G, Touretzky DS, Leen TK (eds) Advances in neural information processing systems. MIT Press, Cambridge, MA, 7 (1994) 925–932Google Scholar
  8. 8.
    Fogelman-Soulie F., Vinnet E., Lamy B.: Multimodular neural network architectures: Application in optical character and human face recognition, Int. J. on Pattern recognition and Artificial Intelligence, 5 (1993) 721–755.CrossRefGoogle Scholar
  9. 9.
    Gorse D., Shepherd, A., Taylor, J.G.: Avoiding local minima by a classical range expansion algorithm. In: I. Aleksander and J. Taylor (eds.) Artificial neural Networks, 2, Elseviere (1992)Google Scholar
  10. 10.
    Haykin, S: Neural networks: A comprehensive foundation, Macmillan College Publishing Company, Inc., NY (1999)MATHGoogle Scholar
  11. 11.
    Myerburg, R.J., , A., Mitrani, R.M.: Frequency of Sudden Cardiac Death and Profiles of Risk. American Journal of Cardiology 80 (5B, 1997) 10F–19F.CrossRefGoogle Scholar
  12. 12.
    Quinlan, P.T.: Structural change and development in real and artificial neural networks. Neural Networks, 11 (1998) 577–599.CrossRefGoogle Scholar
  13. 13.
    Raudys, S.: Evolution and generalization of a single neurone. I. SLP as seven statistical classifiers. Neural Networks 11 (1998) 283–296CrossRefGoogle Scholar
  14. 14.
    Raudys, S.: Scaled rotation regularization. Pattern Recognition, 33 (2000, in press)Google Scholar
  15. 15.
    Raudys, S., Saudargiene, A.: Structures of the covariance matrices in the classifier design. Advances in Pattern Recognition. Springer Lecture notes in computer science. Vol. 1451 (Proc. joint IAPR int. workshops / SSPR’98 and SPR’98, August 11–13, 1998, Sydney, Australia) 583–592CrossRefGoogle Scholar
  16. 16.
    Simson, M.B.: Use of signals in the terminal QRS complex to identify patients with ventricular tachycardia after myocardial infarction. Circulation 64 (1981) 235–242Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Šarūnas Raudys
    • 1
  • Minija Tamošiūnaitė
    • 1
  1. 1.Institute of Mathematics and InformaticsVytautas Magnus UniversityKaunasLithuania

Personalised recommendations