A theoretically grounded application of dropout in recurrent neural networks
- Submitting institution
-
University of Cambridge
- Unit of assessment
- 12 - Engineering
- Output identifier
- 10363
- Type
- D - Journal article
- DOI
-
-
- Title of journal
- Advances in Neural Information Processing Systems
- Article number
- -
- First page
- 1027
- Volume
- 29
- Issue
- -
- ISSN
- 1049-5258
- Open access status
- Out of scope for open access requirements
- Month of publication
- January
- Year of publication
- 2016
- 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
-
1
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The methods developed in this paper are used in industry, e.g. it is the basis of a time series forecasting system at Uber (https://eng.uber.com/neural-networks-uncertainty-estimation/).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -