Title
Transparency Of Execution Using Epigenetic Networks
Authors
Alexander Turner, Nina Dethlefs
Schedule
Date: Friday 8 Sept
Talk Time: TBA
Session: Artificial chemistries and models of cellular dynamics 2 10:30
Keywords
Complex Systems, Computational modelling, Transparent Execution
Abstract
This paper describes how the recurrent connectionist architecture epiNet, which is capable of dynamically modifying its topology, is able to provide a form of transparent execution. EpiNet, which is inspired by eukaryotic gene regulation in nature, is able to break its own architecture down into sets of smaller interacting networks. Twinned with its ability to provide autonomous complex task decomposition, it provides an opportunity to analyse these smaller interacting networks to provide a real world understanding of why specific decisions have been made. We expect work to be useful in fields where the risk of improper decision making is high, such as medical simulations, diagnostics and financial modelling. To test this hypothesis we apply epiNet to two data sets within UCI’s machine learning repository, each of which requires a specific set of behaviours to solve. We then perform analysis on the overall functionality of epiNet in order to deduce the underlying rules behind its functionality.
