Neural network explanation using inversion

  title={Neural network explanation using inversion},
  author={Emad W. Saad and Donald C. Wunsch},
  journal={Neural networks : the official journal of the International Neural Network Society},
  volume={20 1},
An important drawback of many artificial neural networks (ANN) is their lack of explanation capability [Andrews, R., Diederich, J., & Tickle, A. B. (1996). A survey and critique of techniques for extracting rules from trained artificial neural networks. Knowledge-Based Systems, 8, 373-389]. This paper starts with a survey of algorithms which attempt to explain the ANN output. We then present HYPINV, a new explanation algorithm which relies on network inversion; i.e. calculating the ANN input… CONTINUE READING
Highly Cited
This paper has 50 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 25 extracted citations

fewer than 50 Citations

Citations per Year
Semantic Scholar estimates that this publication has 50 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 76 references

A survey and critique

  • R. Andrews, J. Diederich, A. B. Tickle
  • 1996
Highly Influential
8 Excerpts

An evolutionary algorithm for function inversion and boundary marking

  • R. D. Reed, R. Marks
  • In Proceedings of the IEEE international…
  • 1995
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…