"Why ReLU networks yield high-confidence predictions far away from the ..."

Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf (2018)

> Home

Details and statistics

DOI: —

access: open

type: Informal or Other Publication

metadata version: 2019-01-01

- view
  - electronic edition @ arxiv.org (open access)
- export record
  dblp key:
  - journals/corr/abs-1812-05720
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-1812-05720
Matthias Hein, Maksym Andriushchenko, Julian Bitterwolf:
Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem. CoRR abs/1812.05720 (2018)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.