A New Physarum Learner for Network Structure Learning from Biomedical Data

T. Schön, M. Stetter, A. M. Tomé, E. W. Lang

2013

Abstract

A novel structure learning algorithm for Bayesian Networks based on a Physarum Learner is presented. The length of the connections within an initially fully connected Physarum-Maze is taken as the inverse Pearson correlation coefficient between the connected nodes. The Physarum Learner then estimates the shortest indirect paths between each pair of nodes. In each iteration, a score of the surviving edges is incremented. Finally, the highest scored connections are combined to form a Bayesian Network. The novel Physarum Learner method is evaluated with different configurations and compared to the LAGD Hill Climber showing comparable performance with respect to quality of training results and increased time efficiency for large data sets.

Paper Citation

in Harvard Style

Schön T., Stetter M., M. Tomé A. and W. Lang E. (2013). A New Physarum Learner for Network Structure Learning from Biomedical Data . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013) ISBN 978-989-8565-36-5, pages 151-156. DOI: 10.5220/0004227401510156

in Bibtex Style

@conference{biosignals13,
author={T. Schön and M. Stetter and A. M. Tomé and E. W. Lang},
title={A New Physarum Learner for Network Structure Learning from Biomedical Data},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013)},
year={2013},
pages={151-156},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004227401510156},
isbn={978-989-8565-36-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013)
TI - A New Physarum Learner for Network Structure Learning from Biomedical Data
SN - 978-989-8565-36-5
AU - Schön T.
AU - Stetter M.
AU - M. Tomé A.
AU - W. Lang E.
PY - 2013
SP - 151
EP - 156
DO - 10.5220/0004227401510156