Skip to main content

Research Repository

Advanced Search

Transparency of execution using epigenetic networks

Dethlefs, Nina; Turner, Alexander


Alexander Turner


Carole Knibbe

Guillaume Beslon

David Parsons

Dusan Misevic

Jonathan Rouzaud-Cornabas

Nicolas Bredeche

Salima Hassas

Olivier Simonin

Hedi Soula


This paper describes how the recurrent connectionist architecture epiNet, which is capable of dynamically modifying its topology, is able to provide a form of transparent execution. EpiNet, which is inspired by eukaryotic gene regulation in nature, is able to break its own architecture down into sets of smaller interacting networks. This allows for autonomous complex task decomposition, and by analysing these smaller interacting networks, it is possible to provide a real world understanding of why specific decisions have been made. We expect this work to be useful in fields where the risk of improper decision making is high, such as medical simulations, diagnostics and financial modelling. To test this hypothesis we apply epiNet to two data sets within UCI’s machine learning repository, each of which requires a specific set of behaviours to solve. We then perform analysis on the overall functionality of epiNet in order to deduce the underlying rules behind its functionality and in turn provide transparency of execution.


Dethlefs, N., & Turner, A. (2017). Transparency of execution using epigenetic networks. In C. Knibbe, G. Beslon, D. Parsons, D. Misevic, J. Rouzaud-Cornabas, N. Bredeche, …H. Soula (Eds.), Proceedings of the ECAL 2017 (404-411).

Conference Name The European Conference on Artificial Life 2017
Conference Location Lyon, France
Start Date Sep 4, 2017
End Date Sep 8, 2017
Acceptance Date Sep 5, 2017
Publication Date 2017-09
Deposit Date Sep 25, 2017
Journal The European Conference on Artificial Life 2017
Publisher Massachusetts Institute of Technology Press
Peer Reviewed Not Peer Reviewed
Volume 14
Pages 404-411
Book Title Proceedings of the ECAL 2017
ISBN 978-0-262-34633-7
Keywords Transparency; Artificial intelligence; Topological Morphology
Public URL
Publisher URL