Memetic extreme learning machine

Yongshan Zhang, Jia Wu*, Zhihua Cai, Peng Zhang, Ling Chen

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

52 Citations (Scopus)


Extreme Learning Machine (ELM) is a promising model for training single-hidden layer feedforward networks (SLFNs) and has been widely used for classification. However, ELM faces the challenge of arbitrarily selected parameters, e.g., the network weights and hidden biases. Therefore, many efforts have been made to enhance the performance of ELM, such as using evolutionary algorithms to explore promising areas of the solution space. Although evolutionary algorithms can explore promising areas of the solution space, they are not able to locate global optimum efficiently. In this paper, we present a new Memetic Algorithm (MA)-based Extreme Learning Machine (M-ELM for short). M-ELM embeds the local search strategy into the global optimization framework to obtain optimal network parameters. Experiments and comparisons on 46 UCI data sets validate the performance of M-ELM. The corresponding results demonstrate that M-ELM significantly outperforms state-of-the-art ELM algorithms.

Original languageEnglish
Pages (from-to)135-148
Number of pages14
JournalPattern Recognition
Publication statusPublished - 1 Oct 2016
Externally publishedYes


  • extreme Learning Machine
  • self-adaptive
  • memetic algorithm
  • evolutionary machine learning
  • classification

Fingerprint Dive into the research topics of 'Memetic extreme learning machine'. Together they form a unique fingerprint.

Cite this