Skip to main content

Limitations of sensitivity analysis for neural networks in cases with dependent inputs

Publication ,  Journal Article
Mazurowski, MA; Szecówka, PM
Published in: 2006 IEEE International Conference on Computational Cybernetics, ICCC
December 1, 2006

In this paper the limitations of the sensitivity analysis method for feedforward neural networks in the cases of dependent input variables are discussed. First, it is explained that in such cases there can be many functions implemented by neural networks that will accurately approximate training patterns. Then it is pointed out that many of these functions do not allow for proper estimation of the inputs importance using the sensitivity analysis method for neural networks. These two facts are demonstrated to be the reason why one can not completely rely upon the results of this method, when evaluating a real importance of inputs. Examples with graphs visualizing the discussed phenomena are presented. Finally, general conclusions about overall usefulness of the method are introduced.

Duke Scholars

Published In

2006 IEEE International Conference on Computational Cybernetics, ICCC

DOI

Publication Date

December 1, 2006
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Mazurowski, M. A., & Szecówka, P. M. (2006). Limitations of sensitivity analysis for neural networks in cases with dependent inputs. 2006 IEEE International Conference on Computational Cybernetics, ICCC. https://doi.org/10.1109/ICCCYB.2006.305714
Mazurowski, M. A., and P. M. Szecówka. “Limitations of sensitivity analysis for neural networks in cases with dependent inputs.” 2006 IEEE International Conference on Computational Cybernetics, ICCC, December 1, 2006. https://doi.org/10.1109/ICCCYB.2006.305714.
Mazurowski MA, Szecówka PM. Limitations of sensitivity analysis for neural networks in cases with dependent inputs. 2006 IEEE International Conference on Computational Cybernetics, ICCC. 2006 Dec 1;
Mazurowski, M. A., and P. M. Szecówka. “Limitations of sensitivity analysis for neural networks in cases with dependent inputs.” 2006 IEEE International Conference on Computational Cybernetics, ICCC, Dec. 2006. Scopus, doi:10.1109/ICCCYB.2006.305714.
Mazurowski MA, Szecówka PM. Limitations of sensitivity analysis for neural networks in cases with dependent inputs. 2006 IEEE International Conference on Computational Cybernetics, ICCC. 2006 Dec 1;

Published In

2006 IEEE International Conference on Computational Cybernetics, ICCC

DOI

Publication Date

December 1, 2006