Auto-association by multilayer perceptrons and singular value decomposition

  title={Auto-association by multilayer perceptrons and singular value decomposition},
  author={Herv{\'e} Bourlard and Yves Kamp},
  journal={Biological Cybernetics},
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… CONTINUE READING
Highly Influential
This paper has highly influenced 32 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 743 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 391 extracted citations

744 Citations

Citations per Year
Semantic Scholar estimates that this publication has 744 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-8 of 8 references

Image compression by back propagation : a demonstration of extensional programming

  • GW Cottrell, PW Munro, D Zipser
  • 1988
1 Excerpt

Learning internal representations by error propagation

  • DE Rumelhart, GE Hinton, RJ Williams
  • 1986
1 Excerpt

Speaker dependent connected speech recognition via phonemic Markov models

  • H Bourlard, Y Kamp, CJ Wellekens
  • Proc ICASSP,
  • 1985
1 Excerpt

Updating the singular value decomposition

  • JR Bunch, CP Nielsen
  • Numer Math 31:111
  • 1978
1 Excerpt

Least squares , singular values and matrix approximations

  • GH Golub
  • Applikace Matematiky
  • 1968
1 Excerpt

Similar Papers

Loading similar papers…