A topological insight into restricted Boltzmann machines
- Submitting institution
-
Edinburgh Napier University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2006070
- Type
- D - Journal article
- DOI
-
10.1007/s10994-016-5570-z
- Title of journal
- Machine Learning
- Article number
- -
- First page
- 243
- Volume
- 104
- Issue
- 2-3
- ISSN
- 0885-6125
- Open access status
- Compliant
- Month of publication
- July
- 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
-
4
- Research group(s)
-
-
- Citation count
- 24
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper explores novel means to accelerate the training efficiency of Restricted Boltzmann Machines (RBM), one of the very building block of artificial neural networks (ANN). It is significant because it’s one of the first to explore ANNs from the exquisitely novel angle of network science. The paper has significantly influenced a series of follow-up works at the intersection between machine learning and network science. It has made a breakthrough in ANN training, providing a speed-up factor of two orders of magnitude.
It has already been downloaded 5.2K times.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -