Interpretation of Prediction Models Using the Input Gradient

@article{Hechtlinger2016InterpretationOP,
  title={Interpretation of Prediction Models Using the Input Gradient},
  author={Yotam Hechtlinger},
  journal={CoRR},
  year={2016},
  volume={abs/1611.07634}
}
State of the art machine learning algorithms are highly optimized to provide the optimal prediction possible, naturally resulting in complex models. While these models often outperform simpler more interpretable models by order of magnitudes, in terms of understanding the way the model functions, we are often facing a " black box ". In this paper we suggest a simple method to interpret the behavior of any predictive model, both for regression and classification. Given a particular model, the… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 7 times over the past 90 days. VIEW TWEETS
13 Citations
5 References
Similar Papers

Similar Papers

Loading similar papers…