Evolving efficient solutions to complex problems using the Artificial Epigenetic Network

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Published copy (DOI)

Author(s)

Department/unit(s)

Publication details

Title of host publicationInformation Processing in Cells and Tissues
DateE-pub ahead of print - 2 Sep 2015
DatePublished (current) - 2015
Pages153-165
PublisherSpringer
EditorsMichael Lones, Andy Tyrrell, Stephen Smith, Gary Fogel
Original languageEnglish
ISBN (Electronic)978-3-319-23108-2
ISBN (Print)978-3-319-23107-5

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume9303
ISSN (Print)0302-9743

Abstract

The artifcial epigenetic network (AEN) is a computational
model which is able to topologically modify its structure according to
environmental stimulus. This approach is inspired by the functionality
of epigenetics in nature, specically, processes such as chromatin modifications which are able to dynamically modify the topology of gene
regulatory networks. The AEN has previously been shown to perform
well when applied to tasks which require a range of dynamical behaviors
to be solved optimally. In addition, it has been shown that pruning of
the AEN to remove non-functional elements can result in highly com-
pact solutions to complex dynamical tasks. In this work, a method has
been developed which provides the AEN with the ability to self prune
throughout the optimisation process, whilst maintaining functionality.
To test this hypothesis, the AEN is applied to a range of dynamical
tasks and the most optimal solutions are analysed in terms of function
and structure.

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations