Curriculum learning of multiple tasks
- Submitting institution
-
Imperial College of Science, Technology and Medicine
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2398
- Type
- E - Conference contribution
- DOI
-
10.1109/CVPR.2015.7299188
- Title of conference / published proceedings
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- First page
- 5492
- Volume
- -
- Issue
- -
- ISSN
- 1063-6919
- Open access status
- Out of scope for open access requirements
- Month of publication
- October
- Year of publication
- 2015
- 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
- 43
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This algorithm learns the optimal curriculum of tasks for machines, mirroring the human educational process in which subjects are learned in a meaningful order. This curriculum learning strategy enables efficient training of AI machines with theoretical guarantees. The work led to Sharmanska’s Imperial College Research Fellowship.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
