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.

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.

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

• Journal Article Type: Article
• Acceptance Date: Oct 21, 2015
• Online Publication Date: Jan 5, 2016
• Publication Date: 2017-01
• Deposit Date: Jan 7, 2021
• Publicly Available Date: Jan 7, 2021
• Journal: IEEE Transactions on Neural Networks and Learning Systems
• Electronic ISSN: 2162-237X
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 28
• Issue: 1
• Pages: 218-230
• DOI: https://doi.org/10.1109/tnnls.2015.2497142
• Public URL: https://nottingham-repository.worktribe.com/output/5204632
• Publisher URL: https://ieeexplore.ieee.org/document/7372471