Context–aware Learning for Generative Models
- Submitting institution
-
The University of Essex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1480
- Type
- D - Journal article
- DOI
-
10.1109/tnnls.2020.3011671
- Title of journal
- IEEE Transactions on Neural Networks and Learning Systems
- Article number
- -
- First page
- 1
- Volume
- PP
- Issue
- -
- ISSN
- 1045-9227
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2020
- 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
-
3
- Research group(s)
-
B - Brain Computer Interfaces and Neural Engineering (BCI-NE)
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This article, published in IEEE-TNNLS, one of the most reputable, high-impact machine learning journals, augments the author's previous work and proposes novel deep and shallow algorithms for learning from side-information in a completely unsupervised manner. Importantly it provides, not only several real-world application scenaria but also theoretical proofs of the limits and properties of the proposed algorithms. Additional to the theoretical grounding, this context-aware approach was extended to deep generative-models. The theory developed in this work has been successfully applied to the brain-computer-interaction field, leading to another high-impact publication (Journal of Neural Engineering), thus showcasing this manuscript's significant practical implications.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -