Self-adaptive Scouting---Autonomous Experimentation for Systems Biology
Self-adaptive Scouting---Autonomous Experimentation for Systems Biology
We introduce a new algorithm for autonomous experimentation. This algorithm uses evolution to drive exploration during scientific discovery. Population size and mutation strength are self-adaptive. The only variables remaining to be set are the limits and maximum resolution of the parameters in the experiment. In practice, these are determined by instrumentation. Aside from conducting physical experiments, the algorithm is a valuable tool for investigating simulation models of biological systems. We illustrate the operation of the algorithm on a model of HIV-immune system interaction. Finally, the difference between scouting and optimization is discussed.
scientific discovery, evolutionary computing, active learning
52-62
Matsumaru, Naoki
4ef288e1-b713-4bd6-be3f-780e7adf92bc
Centler, Florian
0b06bb3c-fcb8-45c3-9846-532a62be37d4
Zauner, Klaus-Peter
c8b22dbd-10e6-43d8-813b-0766f985cc97
Dittrich, Peter
bef3b5e4-358d-4fa4-abf7-7056c9786a0c
2004
Matsumaru, Naoki
4ef288e1-b713-4bd6-be3f-780e7adf92bc
Centler, Florian
0b06bb3c-fcb8-45c3-9846-532a62be37d4
Zauner, Klaus-Peter
c8b22dbd-10e6-43d8-813b-0766f985cc97
Dittrich, Peter
bef3b5e4-358d-4fa4-abf7-7056c9786a0c
Matsumaru, Naoki, Centler, Florian, Zauner, Klaus-Peter and Dittrich, Peter
(2004)
Self-adaptive Scouting---Autonomous Experimentation for Systems Biology.
Raidl, G. R., Cagnoni, S., Branke, J., Corne, D., Drechsler, R., Jin, Y., Johnson, C. G., Machado, P., Marchiori, E., Rothlauf, F., Smith, G. D. and Squillero, G.
(eds.)
In Lecture Notes in Artificial Intelligence, Vol. 3005.
Springer Berlin.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
We introduce a new algorithm for autonomous experimentation. This algorithm uses evolution to drive exploration during scientific discovery. Population size and mutation strength are self-adaptive. The only variables remaining to be set are the limits and maximum resolution of the parameters in the experiment. In practice, these are determined by instrumentation. Aside from conducting physical experiments, the algorithm is a valuable tool for investigating simulation models of biological systems. We illustrate the operation of the algorithm on a model of HIV-immune system interaction. Finally, the difference between scouting and optimization is discussed.
Text
MatsumaruN04SelfAdptScout.pdf
- Other
More information
Published date: 2004
Venue - Dates:
2nd European Workshop on Evolutionary Bioinformatics, 2004-01-01
Keywords:
scientific discovery, evolutionary computing, active learning
Organisations:
Agents, Interactions & Complexity
Identifiers
Local EPrints ID: 258781
URI: http://eprints.soton.ac.uk/id/eprint/258781
PURE UUID: 94cef7f4-110b-4d8a-83a4-2a058eb3dde6
Catalogue record
Date deposited: 20 Feb 2004
Last modified: 14 Mar 2024 06:13
Export record
Contributors
Author:
Naoki Matsumaru
Author:
Florian Centler
Author:
Klaus-Peter Zauner
Author:
Peter Dittrich
Editor:
G. R. Raidl
Editor:
S. Cagnoni
Editor:
J. Branke
Editor:
D. Corne
Editor:
R. Drechsler
Editor:
Y. Jin
Editor:
C. G. Johnson
Editor:
P. Machado
Editor:
E. Marchiori
Editor:
F. Rothlauf
Editor:
G. D. Smith
Editor:
G. Squillero
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics