Learning Understandable Neural Networks With Nonnegative Weight Constraints

  title={Learning Understandable Neural Networks With Nonnegative Weight Constraints},
  author={Jan Chorowski and Jacek M. Zurada},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
People can understand complex structures if they relate to more isolated yet understandable concepts. Despite this fact, popular pattern recognition tools, such as decision tree or production rule learners, produce only flat models which do not build intermediate data representations. On the other hand, neural networks typically learn hierarchical but opaque models. We show how constraining neurons' weights to be nonnegative improves the interpretability of a network's operation. We analyze the… CONTINUE READING
Highly Cited
This paper has 65 citations. REVIEW CITATIONS
24 Extracted Citations
35 Extracted References
Similar Papers

Citing Papers

Publications influenced by this paper.
Showing 1-10 of 24 extracted citations

66 Citations

Citations per Year
Semantic Scholar estimates that this publication has 66 citations based on the available data.

See our FAQ for additional information.

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 35 references

Similar Papers

Loading similar papers…