Skip to main content

Research Repository

See what's under the surface

Artificial epigenetic networks: automatic decomposition of dynamical control tasks using topological self-modification

Turner, Alexander P.; Caves, Leo S. D.; Stepney, Susan; Tyrrell, Andy M.; Lones, Michael A.

Authors

Leo S. D. Caves

Susan Stepney

Andy M. Tyrrell

Michael A. Lones



Abstract

This paper describes the artificial epigenetic network, a recurrent connectionist architecture that is able to dynamically modify its topology in order to automatically decompose and solve dynamical problems. The approach is motivated by the behavior of gene regulatory networks, particularly the epigenetic process of chromatin remodeling that leads to topological change and which underlies the differentiation of cells within complex biological organisms. We expected this approach to be useful in situations where there is a need to switch between different dynamical behaviors, and do so in a sensitive and robust manner in the absence of a priori information about problem structure. This hypothesis was tested using a series of dynamical control tasks, each requiring solutions that could express different dynamical behaviors at different stages within the task. In each case, the addition of topological self-modification was shown to improve the performance and robustness of controllers. We believe this is due to the ability of topological changes to stabilize attractors, promoting stability within a dynamical regime while allowing rapid switching between different regimes. Post hoc analysis of the controllers also demonstrated how the partitioning of the networks could provide new insights into problem structure.

Journal Article Type Article
Publication Date 2017-01
Journal IEEE transactions on neural networks and learning systems
Print ISSN 2162-237X
Electronic ISSN 2162-2388
Publisher Institute of Electrical and Electronics Engineers
Peer Reviewed Peer Reviewed
Volume 28
Issue 1
Pages 218-230
Institution Citation Turner, A. P., Caves, L. S. D., Stepney, S., Tyrrell, A. M., & Lones, M. A. (2017). Artificial epigenetic networks: automatic decomposition of dynamical control tasks using topological self-modification. IEEE Transactions on Neural Networks and Learning Systems, 28(1), 218-230. https://doi.org/10.1109/TNNLS.2015.2497142
DOI https://doi.org/10.1109/TNNLS.2015.2497142
Keywords Epigenetic networks, Recurrent neural networks (RNNs), Self-modification, Intelligent control, Task decomposition
Publisher URL http://ieeexplore.ieee.org/document/7372471/
Additional Information Copy of article first published in: IEEE transactions on neural networks and learning systems, 2017, v.28, issue 1

Files

Article.pdf (4.1 Mb)
PDF

Copyright Statement
This work is licensed under a Creative Commons Attribution 3.0 License. For more information, see http://creativecommons.org/licenses/by/3.0/





You might also like



Downloadable Citations