English

Towards Dependability Metrics for Neural Networks

Machine Learning 2018-06-11 v2 Machine Learning

Abstract

Artificial neural networks (NN) are instrumental in realizing highly-automated driving functionality. An overarching challenge is to identify best safety engineering practices for NN and other learning-enabled components. In particular, there is an urgent need for an adequate set of metrics for measuring all-important NN dependability attributes. We address this challenge by proposing a number of NN-specific and efficiently computable metrics for measuring NN dependability attributes including robustness, interpretability, completeness, and correctness.

Keywords

Cite

@article{arxiv.1806.02338,
  title  = {Towards Dependability Metrics for Neural Networks},
  author = {Chih-Hong Cheng and Georg Nührenberg and Chung-Hao Huang and Harald Ruess and Hirotoshi Yasuoka},
  journal= {arXiv preprint arXiv:1806.02338},
  year   = {2018}
}
R2 v1 2026-06-23T02:21:34.944Z