Artificial Epigenetic Networks : Automatic Decomposition of Dynamical Control Tasks using Topological Self-Modification
- Submitting institution
-
Heriot-Watt University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 10593626
- Type
- D - Journal article
- DOI
-
10.1109/TNNLS.2015.2497142
- Title of journal
- IEEE Transactions on Neural Networks and Learning Systems
- Article number
- -
- First page
- 218
- Volume
- 28
- Issue
- 1
- ISSN
- 2162-237X
- 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
-
4
- Research group(s)
-
-
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Published in one of the highest cited computer science journals (IF 11.7 in 2018), this is an output of a £600k EPSRC-funded project (EP/F060041/1). It demonstrates how neural network architectures can be improved by looking at the organisation of biochemical networks found within animal cells, and how this approach is complementary to traditional brain-inspired approaches. When used to model complex systems, the epigenetic architecture also allows understanding of the dynamical structure of the system being modelled. This has led to a new EPSRC project (EP/S003207/1), where the approach is being used to understand human visceral leismaniasis.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
