ELM-SOM+: A continuous mapping for visualization

Renjie Hu*, Karl Ratner, Edward Ratner, Yoan Miche, Kaj Mikael Björk, Amaury Lendasse

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

3 Citations (Scopus)

Abstract

This paper presents a novel dimensionality reduction technique based on ELM and SOM: ELM-SOM+. This technique preserves the intrinsic quality of Self-Organizing Map (SOM): it is nonlinear and suitable for big data. It also brings continuity to the projection using two Extreme Learning Machine (ELM) models, the first one to perform the dimensionality reduction and the second one to perform the reconstruction. ELM-SOM+ is tested successfully on nine diverse datasets. Regarding reconstruction error, the new methodology shows considerable improvement over SOM and brings continuity.

Original languageEnglish
Peer-reviewed scientific journalNeurocomputing
Volume365
Pages (from-to)147-156
Number of pages10
ISSN0925-2312
DOIs
Publication statusPublished - 06.11.2019
MoE publication typeA1 Journal article - refereed

Keywords

  • Self-Organizing Maps
  • Visualization
  • 512 Business and Management
  • Dimensionality reduction techniques
  • Visualization
  • Extreme Learning Machines
  • Self-Organizing Maps
  • Machine learning
  • Neural networks

Fingerprint Dive into the research topics of 'ELM-SOM+: A continuous mapping for visualization'. Together they form a unique fingerprint.

  • Cite this

    Hu, R., Ratner, K., Ratner, E., Miche, Y., Björk, K. M., & Lendasse, A. (2019). ELM-SOM+: A continuous mapping for visualization. Neurocomputing, 365, 147-156. https://doi.org/10.1016/j.neucom.2019.06.093