Reachability Analysis of Deep Neural Networks with Provable Guarantees
- Submitting institution
-
University of Exeter
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 6410
- Type
- E - Conference contribution
- DOI
-
10.24963/ijcai.2018/368
- Title of conference / published proceedings
- Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, July 13-19, 2018, Stockholm, Sweden
- First page
- 2651
- Volume
- 7
- Issue
- 6
- ISSN
- 1045-0823
- Open access status
- Technical exception
- Month of publication
- -
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is one of the very first works on reachability analysis of modern deep neural networks (DNNs) and its general framework enables safety verification, output range analysis, and robustness quantification for various types of DNNs. This work is one of the most important research outcomes in a £5 million EPSRC Mobile Autonomy Programme Grant: Safety, Trust and Integrity. Its methodology also directly resulted in a £2 million ERC Advanced Grant: FUN2MODEL: From Function-based to model-based automated probabilistic reasoning for Deep Learning.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -