Turner, Alexander Phillip, Caves, Leo orcid.org/0000-0002-8610-1114, Stepney, Susan orcid.org/0000-0003-3146-5401 et al. (2 more authors) (2017) Artificial Epigenetic Networks:Automatic Decomposition of Dynamical Control Tasks using Topological Self-Modification. IEEE transactions on neural networks and learning systems. 7372471. pp. 218-230. ISSN 2162-237X
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.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © Copyright IEEE 2016. This content is made available by the publisher under a Creative Commons Attribution Licence. |
Keywords: | Epigenetic networks,intelligent control,recurrent neural networks (RNNs),self-modification,task decomposition |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Electronic Engineering (York) The University of York > Faculty of Sciences (York) > Computer Science (York) The University of York > Faculty of Sciences (York) > Biology (York) |
Funding Information: | Funder Grant number EPSRC EP/K040820/1 |
Depositing User: | Pure (York) |
Date Deposited: | 01 Feb 2016 13:30 |
Last Modified: | 07 Feb 2025 00:12 |
Published Version: | https://doi.org/10.1109/TNNLS.2015.2497142 |
Status: | Published |
Refereed: | Yes |
Identification Number: | 10.1109/TNNLS.2015.2497142 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:93468 |
Download
Filename: Turner_et_al_ArtificialEpigeneticNetworks_TNNLS.pdf
Description: Turner_et_al_ArtificialEpigeneticNetworks_TNNLS