Biological Cybernetics

, Volume 59, Issue 4–5, pp 291–294 | Cite as

Auto-association by multilayer perceptrons and singular value decomposition

  • H. Bourlard
  • Y. Kamp


The multilayer perceptron, when working in auto-association mode, is sometimes considered as an interesting candidate to perform data compression or dimensionality reduction of the feature space in information processing applications. The present paper shows that, for auto-association, the nonlinearities of the hidden units are useless and that the optimal parameter values can be derived directly by purely linear techniques relying on singular value decomposition and low rank matrix approximation, similar in spirit to the well-known Karhunen-Loève transform. This approach appears thus as an efficient alternative to the general error back-propagation algorithm commonly used for training multilayer perceptrons. Moreover, it also gives a clear interpretation of the rôle of the different parameters.


Feature Space Dimensionality Reduction Processing Application Data Compression Multilayer Perceptrons 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Ahmed N, Rao KR (1975) Orthogonal transforms for digital signal processing. Springer, New York Berlin HeidelbergCrossRefGoogle Scholar
  2. Bourlard H, Kamp Y, Wellekens CJ (1985) Speaker dependent connected speech recognition via phonemic Markov models. Proc ICASSP, pp 1213–1216Google Scholar
  3. Bunch JR, Nielsen CP (1978) Updating the singular value decomposition. Numer Math 31:111–129CrossRefGoogle Scholar
  4. Cottrell GW, Munro PW, Zipser D (1988) Image compression by back propagation: a demonstration of extensional programming. In: Sharkey NE (ed) Advances in cognitive science, vol 2. Abbex, Norwood, (NJ) (in press)Google Scholar
  5. Delsarte P, Kamp Y (1988) Low rank matrices with a given sign pattern Philips Research Laboratory, Brussels SIAM J: (to be published)Google Scholar
  6. Elman JL, Zipser D (1987) Learning the hidden structure of speech. J Acoust Soc Am 83:1615–1626CrossRefGoogle Scholar
  7. Golub GH (1968) Least squares, singular values and matrix approximations. Applikace Matematiky 13:44–51Google Scholar
  8. Golub GH, Van Loan CF (1983) Matrix computations. North Oxford Academic, OxfordGoogle Scholar
  9. Harrison TD (1987) A Connectionist framework for continuous speech recognition. Cambridge University Ph. D. dissertationGoogle Scholar
  10. Lippmann RP (1987) An introduction to computing with neural nets. IEEE ASSP Magazine, pp 4–22Google Scholar
  11. Minsky M, Papert S (1969) Perceptrons. MIT Press, CambridgeGoogle Scholar
  12. Rumelhart DE, McClellarnd JL, and the PDP Research Group (1986) Parallel distributed processing. Exploration in the microstructure of cognition. vol 1–2. MIT Press, CambridgeGoogle Scholar
  13. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. In: Rumelhart DE, McClellan JL (eds) Parallel distributed processing. Exploration in the microstructure of cognition, vol 1. Foundations. MIT Press, CambridgeGoogle Scholar
  14. Stewart GW (1973) Introduction to matrix computations. Academic Press, New YorkGoogle Scholar

Copyright information

© Springer-Verlag 1988

Authors and Affiliations

  • H. Bourlard
    • 1
  • Y. Kamp
    • 1
  1. 1.Philips Research LaboratoryBrusselsBelgium

Personalised recommendations