@INPROCEEDINGS{MraPet14icann,
  author = {Iveta Mrázová and Zuzana Petříčková},
  title = {Fast Sensitivity-Based Training of BP-Networks},
  booktitle = {Artificial Neural Networks and Machine Learning -- {ICANN} 2014 --
    24th International Conference on Artificial Neural Networks, Hamburg,
    Germany, September 15--19, 2014. Proceedings},
  year = {2014},
  editor = {Stefan Wermter and Cornelius Weber and Wlodzislaw Duch and Timo Honkela
    and Petia D. Koprinkova{-}Hristova and Sven Magg and G{\"{u}}nther
    Palm and Alessandro E. P. Villa},
  volume = {8681},
  series = {Lecture Notes in Computer Science},
  pages = {507--514},
  address = {Berlin, Heidelberg},
  publisher = {Springer},
  bibsource = {dblp computer science bibliography, http://dblp.org},
  biburl = {http://dblp.uni-trier.de/rec/bib/conf/icann/MrazovaP14},
  crossref = {DBLP:conf/icann/2014},
  doi = {10.1007/978-3-319-11179-7_64},
  isbn = {978-3-319-11178-0},
  timestamp = {Mon, 08 Sep 2014 13:53:08 +0200},
  url = {http://dx.doi.org/10.1007/978-3-319-11179-7_64},
  abstract = {Sensitivity analysis became an acknowledged tool used to study the performance of artificial neural networks. Sensitivity analysis allows to assess the influence, e.g., of each neuron or weight on the final network output. In particular various feature selection and pruning strategies are based on this capability. In this paper, we will present a new approximative sensitivity-based training algorithm yielding robust neural networks with generalization capabilities comparable to its exact analytical counterpart, yet much faster.}
}