A further investigation on the reliability of extreme learning machines

Yanxing Hu, Yuan Wang, Jia You, Jame N.K. Liu, Yulin He

Research output: Journal article publicationConference articleAcademic researchpeer-review


Research community has recently put more attention to the Extreme Learning Machines (ELMs) algorithm in Neural Network (NN) area. The ELMs are much faster than the traditional gradient-descent-based learning algorithms due to its analytical determination of output weights with the random choice of input weights and hidden layer bias. However, since the input weights and bias are randomly assigned and not adjusted, the ELMs model shows an instability if we repeat the experiments many times. Such instability makes the ELMs less reliable than other computational intelligence models. In our investigation, we try to solve this problem by using the Random Production in the first layer of the ELMs. Thus, we can reduce the chance of using random weight assignment in ELMs by removing the bias in the hidden layer. Experiment son different data sets demonstrate that the proposed model has higher stability and reliability than the classical ELMs.
Original languageEnglish
Article number7022710
Pages (from-to)1031-1037
Number of pages7
JournalIEEE International Conference on Data Mining Workshops, ICDMW
Issue numberJanuary
Publication statusPublished - 1 Jan 2015
Event14th IEEE International Conference on Data Mining Workshops, ICDMW 2014 - Shenzhen, China
Duration: 14 Dec 2014 → …


  • Extreme Learning Machine
  • Random Projection
  • Random weight Assignment

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Cite this