A modified extreme learning machine with sigmoidal activation functions

Zhixiang X. Chen, Houying Y. Zhu, Yuguang G. Wang

Research output: Contribution to journalArticlepeer-review

38 Citations (Scopus)


This paper proposes a modified ELM algorithm that properly selects the input weights and biases before training the output weights of single-hidden layer feedforward neural networks with sigmoidal activation function and proves mathematically the hidden layer output matrix maintains full column rank. The modified ELM avoids the randomness compared with the ELM. The experimental results of both regression and classification problems show good performance of the modified ELM algorithm.
Original languageEnglish
Pages (from-to)541–550
Number of pages10
JournalNeural Computing and Applications
Issue number3-4
Publication statusPublished - Mar 2013
Externally publishedYes


  • Feedforward neural networks
  • Extreme learning machine
  • Moore–Penrose generalized inverse


Dive into the research topics of 'A modified extreme learning machine with sigmoidal activation functions'. Together they form a unique fingerprint.

Cite this