FCNN : Fourier Convolutional Neural Networks
- Submitting institution
-
The University of Lancaster
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 279954053
- Type
- E - Conference contribution
- DOI
-
10.1007/978-3-319-71249-9_47
- Title of conference / published proceedings
- Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2017, Proceedings
- First page
- 786
- Volume
- 10534
- Issue
- -
- ISSN
- 0302-9743
- Open access status
- Technical exception
- Month of publication
- December
- Year of publication
- 2017
- 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 - Data Science
- Citation count
- 7
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposes a novel approach to reducing excessive training time in deep learning image analysis, moving the bulk of computation to the Fourier domain, and addresses the resulting challenges. This can be built into most architectures and considerable improvement is thoroughly demonstrated. This was published in the European Conference on Machine Learning, one of the top conferences on machine learning, and highlighted by BBVA Data and Analytics as “arousing great interest”. This work has resulted in an invited talk to the RCOphth, further research and formed a significant part of a £300k grant application (pending).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
