Linear order statistic neuron

Authors

Charlie Veal, University of Missouri
Alex Yang, University of Missouri
Alex Hurt, University of Missouri
Muhammad Aminul Islam, University of Missouri
Derek T. Anderson, University of Missouri
Grant Scott, University of Missouri
James M. Keller, University of Missouri
Timothy C. Havens, Michigan Technological UniversityFollow

Document Type

Conference Proceeding

Publication Date

10-10-2019

Department

Department of Electrical and Computer Engineering

Abstract

Herein, a generalization of the ordered weighted average (OWA) is put forth relative to pattern recognition. The resultant linear order statistic neuron (LOSN) is unique in that it bridges fuzzy sets, specifically fuzzy data/information aggregation, with neural networks. This article discusses the gradient descent-based optimization and geometric interpretation of the LOSN. An advantage is that the LOSN is an efficient shared weight encoding of N! perceptrons, relative to N inputs. Open source codes are provided to facilitate reproducible research. Experiments are conducted to both validate the method and show its non-linear geometric expression.

Publisher's Statement

© 2019 IEEE. Publisher’s version of record: https://doi.org/10.1109/FUZZ-IEEE.2019.8858802

Publication Title

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

Recommended Citation

Veal, C., Yang, A., Hurt, A., Islam, M. A., Anderson, D. T., Scott, G., Keller, J. M., & Havens, T. C. (2019). Linear order statistic neuron. 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). http://doi.org/10.1109/FUZZ-IEEE.2019.8858802
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/931