Transfer learning for the Choquet integral

Authors

Bryce Murray, University of Missouri
Muhammad Aminul Islam, University of Missouri
Anthony Pinar, Michigan Technological UniversityFollow
Derek T. Anderson, University of Missouri
Grant Scott, University of Missouri
Timothy C. Havens, Michigan Technological UniversityFollow
et al.

Document Type

Conference Proceeding

Publication Date

10-10-2019

Department

Department of Electrical and Computer Engineering

Abstract

The Choquet integral (ChI) is a proven tool for information aggregation. In prior work, we showed that learning a ChI from data results in missing variables. Herein, we explore two ways to transfer a known ChI from a source domain to a new under sampled target domain. The first method is based on regularization and it listens to the full source domain ChI. The second method optimizes what we can observe (target domain supported variables) and missing variables are the only thing migrated from the source domain. Synthetic experiments, aka we know the truth, are used to show the behavior of these methods with respect to transfering between ChIs.

Publisher's Statement

© 2019 IEEE. Publisher’s version of record: https://doi.org/10.1109/FUZZ-IEEE.2019.8858844

Publication Title

2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

Recommended Citation

Murray, B., Islam, M. A., Pinar, A., Anderson, D. T., Scott, G., Havens, T. C., & et al. (2019). Transfer learning for the Choquet integral. 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). http://doi.org/10.1109/FUZZ-IEEE.2019.8858844
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/932