Input variable selection using independent component analysis

  title={Input variable selection using independent component analysis},
  author={Andrew D. Back and Thomas P. Trappenberg},
Theproblemof inputvariableselectionis well knownin the task of modelingreal world data. In this paper , we proposea novelmodel-freealgorithmfor input variableselection usingindependent componentanalysisandhigherorder crossstatistics. Experimentalresultsare givenwhich indicatethat the methodis capableof giving reliable performanceand that it outperformsother approacheswhen theinputsare dependent. 
Highly Cited
This paper has 20 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.
13 Citations
7 References
Similar Papers


Publications referenced by this paper.
Showing 1-7 of 7 references

Dimensionreductionby localprincipalcomponentanalysis,

  • Nandakishore Kambhatla, Todd K. Leen
  • Neural Computation,
  • 1997
1 Excerpt

Fast pruningusingprincipal components,

  • Asriel U. Levin, Todd K. Leen, andJohnE. Moody
  • Kendall ’ s Advanced Theory of Statistics : Sixth…
  • 1994
1 Excerpt

Leen , “ Dimension reduction by local principal component analysis

  • Jack D. Cowan, Gerald Tesauro
  • Advances in Neural Information Processing Systems
  • 1994

Ord, Kendall’s AdvancedTheoryof Statistics: SixthEdition Volume1

  • A. StuartandK
  • 1994
1 Excerpt

Selecting input variables using mutual information and nonparamteric density etimation

  • A. S. Weigend
  • Proceedings of the 1994 International Symposium…
  • 1994

Selectinginput variablesusingmutualinformationandnonparamtericdensityestimation,

  • B. V. BonnlanderandA.S. Weigend
  • Proceedingsof the 1994InternationalSymposiumon…
  • 1994
2 Excerpts

Blind separationof sources,PartI: An adapti ve algorithmbasedon neuromimeticarchitecture,

  • C. JuttenandJ.Herault
  • SignalProcessing,
  • 1991
1 Excerpt

Similar Papers

Loading similar papers…