A fast learning algorithm for multi-layer extreme learning machine

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

17 Scopus Citations
View graph of relations

Author(s)

  • Jiexiong Tang
  • Chenwei Deng
  • Guang-Bin Huang
  • Junhui Hou

Detail(s)

Original languageEnglish
Title of host publication2014 IEEE International Conference on Image Processing, ICIP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages175-178
ISBN (Print)9781479957514
Publication statusPublished - 28 Jan 2014
Externally publishedYes

Abstract

Extreme learning machine (ELM) is an efficient training algorithm originally proposed for single-hidden layer feedforward networks (SLFNs), of which the input weights are randomly chosen and need not to be fine-tuned. In this paper, we present a new stack architecture for ELM, to further improve the learning accuracy of ELM while maintaining its advantage of training speed. By exploiting the hidden information of ELM random feature space, a recovery-based training model is developed and incorporated into the proposed ELM stack architecture. Experimental results of the MNIST handwriting dataset demonstrate that the proposed algorithm achieves better and much faster convergence than the state-of-the-art ELM and deep learning methods.

Research Area(s)

  • deep learning, Extreme learning machine (ELM), multi-layer training, sparse representation

Citation Format(s)

A fast learning algorithm for multi-layer extreme learning machine. / Tang, Jiexiong; Deng, Chenwei; Huang, Guang-Bin; Hou, Junhui.

2014 IEEE International Conference on Image Processing, ICIP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 175-178 7025034.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review