|
Digital Library of the
European Council for Modelling and Simulation |
Title: |
Autonomous Design Of Modular
Intelligent Systems |
Authors: |
Pavel Nahodil, Jaroslav
Vitku |
Published in: |
(2013).ECMS 2013 Proceedings edited
by: W. Rekdalsbakken, R. T. Bye, H. Zhang European Council for Modeling
and Simulation. doi:10.7148/2013 ISBN:
978-0-9564944-6-7 27th
European Conference on Modelling and Simulation, Aalesund, Norway, May 27th –
30th, 2013 |
Citation
format: |
Pavel Nahodil,
Jaroslav Vitku (2013).
Autonomous Design Of Modular Intelligent Systems,
ECMS 2013 Proceedings edited by: W. Rekdalsbakken, R. T. Bye, H. Zhang, European Council for Modeling
and Simulation. doi:10.7148/2013-0379 |
DOI: |
http://dx.doi.org/10.7148/2013-0379 |
Abstract: |
We
propose our original system capable of autonomous design of general-purpose
complex modular hybrid systems. The resulting hybrid systems will be able to
employ various techniques of learning, decisionmaking,
prediction etc. Presented topic is from Artificial Life domain, but
contributes also to fields such as Artificial Intelligence, Biology,
Computational Neuroscience, Ethology, Cybernetics and potentially into many other aspects of
research. The autonomous design is implemented as an optimization of system
topology with respect to given problem. The principle of design is based on
modified neuro-evolution and can be compared to
modular neural networks. One of the main requirements is standardization of
communication between very different subsystems. Here, each subsystem -
module implements arbitrary algorithm and is treated as a Multiple-Input
Multiple-Output subsystem. First, the design of simulator used is described,
then the basic principle of hybrid networks is explained with it benefits and
drawbacks. Finally, simple example is mentioned. |
Full
text: |