Evolving extreme learning machine paradigm with adaptive operator selection and parameter control

Ke LI, Ran WANG, Sam KWONG, Jingjing CAO

Research output: Journal PublicationsJournal Article (refereed)peer-review

13 Citations (Scopus)


Extreme Learning Machine (ELM) is an emergent technique for training Single-hidden Layer Feedforward Networks (SLFNs). It attracts significant interest during the recent years, but the randomly assigned network parameters might cause high learning risks. This fact motivates our idea in this paper to propose an evolving ELM paradigm for classification problems. In this paradigm, a Differential Evolution (DE) variant, which can online select the appropriate operator for offspring generation and adaptively adjust the corresponding control parameters, is proposed for optimizing the network. In addition, a 5-fold cross validation is adopted in the fitness assignment procedure, for improving the generalization capability. Empirical studies on several real-world classification data sets have demonstrated that the evolving ELM paradigm can generally outperform the original ELM as well as several recent classification algorithms. © World Scientific Publishing Company.
Original languageEnglish
Pages (from-to)143-154
JournalInternational Journal of Uncertainty, Fuzziness and Knowlege-Based Systems
Issue numberSUPPL.2
Publication statusPublished - Dec 2013
Externally publishedYes


  • Adaptive operator selection
  • Differential evolution
  • Extreme learning machine
  • Parameter control


Dive into the research topics of 'Evolving extreme learning machine paradigm with adaptive operator selection and parameter control'. Together they form a unique fingerprint.

Cite this