Artificial Epigenetic Networks

Our paper “Artificial Epigenetic Networks: Automatic Decomposition of Dynamical Control Tasks using Topological Self-Modification” has just been published in the journal IEEE Transactions on Neural Networks and Learning Systems.  It has been available “early on line” for some time, but this is the official publication, with volume number and everything.

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.

It is open access and can be found at doi:10.1109/TNNLS.2015.2497142

When I say it has been available on line “for some time”, I’m not kidding.  Look at the footnote on the first page:

Manuscript received February 17, 2015; revised October 19, 2015; accepted October 21, 2015. Date of publication December 24, 2015; date of current version December 22, 2016

The bibliographic information is:

Volume: 28, Issue: 1, Jan. 2017