Auto-association by multilayer perceptrons and singular value decomposition

@article{Bourlard1988AutoassociationBM,
  title={Auto-association by multilayer perceptrons and singular value decomposition},
  author={Herv{\'e} Bourlard and Yves Kamp},
  journal={Biological Cybernetics},
  year={1988},
  volume={59},
  pages={291-294}
}

• Hervé Bourlard, Yves Kamp
• Published in Biological Cybernetics 1988
• DOI:10.1007/BF00332918

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

View on Springer

BETA

Alternate Sources

Save to Library

Create Alert

Cite