Distance-based Confidence Score for Neural Network Classifiers

@article{Mandelbaum2017DistancebasedCS,
  title={Distance-based Confidence Score for Neural Network Classifiers},
  author={Amit Mandelbaum and Daphna Weinshall},
  journal={CoRR},
  year={2017},
  volume={abs/1709.09844}
}
The reliable measurement of confidence in classifiers’ predictions is very important for many applications, and is therefore an important part of classifier design. Yet, although deep learning has received tremendous attention in recent years, not much progress has been made in quantifying the prediction confidence of neural network classifiers. Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with prohibitive computational costs. In… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 48 times over the past 90 days. VIEW TWEETS
7 Citations
35 References
Similar Papers

References

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

Fast and accurate deep network learning by exponential linear units (elus)

  • Clevert, Djork-Arné, Unterthiner, Thomas, Hochreiter, Sepp
  • arXiv preprint arXiv:1511.07289,
  • 2015
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…