Active Learning Based on Single-Hidden Layer Feed-Forward Neural Network

Ran WANG, Sam KWONG, Qingshan JIANG, Ka-Chun WONG

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

3 Citations (Scopus)


In this paper, we propose two stream-based active learning algorithms for single-hidden layer feed-forward neural networks (SLFNs) trained by extreme learning machine (ELM). Uncertainty and inconsistency are adopted as two sample selection criteria. Uncertainty reflects the nondeterminacy of a sample among different decision classes, which is calculated by information entropy or Gini-index. Inconsistency reflects the disagreement of the sample between its conditional features and decision labels, which is calculated by the lower approximations in fuzzy rough sets. Experimental results demonstrate that inconsistency-based strategy is more effective than uncertainty based strategy for SLFNs under stream-based environment.
Original languageEnglish
Title of host publicationProceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015
Publication statusPublished - 12 Jan 2016
Externally publishedYes

Bibliographical note

National Natural Science Foundation of China under Grant 61402460


  • Active Learning
  • Extreme Learning Machine
  • Inconsistency
  • SLFNs
  • Uncertainty


Dive into the research topics of 'Active Learning Based on Single-Hidden Layer Feed-Forward Neural Network'. Together they form a unique fingerprint.

Cite this