A Unified view of piecewise linear neural network verification
- Submitting institution
-
University of Oxford
- Unit of assessment
- 12 - Engineering
- Output identifier
- 9466
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Advances in Neural Information Processing Systems 2018
- First page
- 4790
- Volume
- 31
- Issue
- -
- ISSN
- 1049-5258
- Open access status
- Exception within 3 months of publication
- Month of publication
- November
- 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
-
4
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper is a result of a collaboration between Oxford and DeepMind (Principal Scientist, DeepMind available to corroborate). This is the first paper to present a unified framework for verification of neural networks. It forms the basis of two other papers (one accepted in JMLR, one accepted as full oral in ICLR 2020). The work was presented in two invited tutorials (VMCAI 2019 Winter School and Imperial College Machine Learning Tutorial 2019). The results were used in the following projects: ERC grant ERC-2012-AdG 321162-HELIOS, EPSRC grant Seebibyte EP/M013774/1 and EPSRC/MURI grant EP/N019474/1.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -