Journal article · 2015 · Open access

Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm

Mark D. McDonnell, Migel D. Tissera, Tony Vladusich, van Schaik André, Jonathan C. Tapson

PLoS ONE, 10(8), e0134254 · Published 11 August 2015 · DOI 10.1371/journal.pone.0134254

Free PDFView at the publisherCite this paper

In brief

“Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm” is a 2015 journal article by Mark D. McDonnell and 4 co-authors, published in PLoS ONE. OpenAlex counts 89 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at PLoS ONE.

Citations
89
Most cited in
2019 (16)
Field-weighted impact
9.57
References
39
Authors
5

Abstract

Recent advances in training deep (multi-layer) architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image and speech recognition. However, here we show that error rates below 1% on the MNIST handwritten digit benchmark can be replicated with shallow non-convolutional neural networks. This is achieved by training such networks using the 'Extreme Learning Machine' (ELM) approach, which also enables a very rapid training time (∼ 10 minutes). Adding distortions, as is common practise for MNIST, reduces error rates even further. Our methods are also shown to be capable of achieving less than 5.5% error rates on the NORB image database. To achieve these results, we introduce several enhancements to the standard ELM algorithm, which individually and in combination can significantly improve performance. The main innovation is to ensure each hidden-unit operates only on a randomly sized and positioned patch of each image. This form of random 'receptive field' sampling of the input ensures the input weight matrix is sparse, with about 90% of weights equal to zero. Furthermore, combining our methods with a small number of iterations of a single-batch backpropagation method can significantly reduce the number of hidden-units required to achieve a particular performance. Our close to state-of-the-art results for MNIST and NORB suggest that the ease of use and accuracy of the ELM algorithm for designing a single-hidden-layer neural network classifier should cause it to be given greater consideration either as a standalone method for simpler problems, or as the final classification stage in deep neural networks applied to more difficult problems.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

McDonnell, M. D., Tissera, M. D., Vladusich, T., André, V. S., & Tapson, J. C. (2015). Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm. PLoS ONE, 10(8), e0134254. https://doi.org/10.1371/journal.pone.0134254

MLA 9

McDonnell, Mark D., et al. “Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm.” PLoS ONE, vol. 10, no. 8, 2015, p. e0134254. https://doi.org/10.1371/journal.pone.0134254.

Chicago

McDonnell, Mark D., Migel D. Tissera, Tony Vladusich, van Schaik André, and Jonathan C. Tapson. 2015. “Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm.” PLoS ONE 10 (8): e0134254. https://doi.org/10.1371/journal.pone.0134254.

Harvard

McDonnell, M. D. et al. (2015) ‘Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm’, PLoS ONE, 10(8), p. e0134254. doi:10.1371/journal.pone.0134254.

IEEE

M. D. McDonnell, M. D. Tissera, T. Vladusich, V. S. André, and J. C. Tapson, “Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm,” PLoS ONE, vol. 10, no. 8, p. e0134254, 2015, doi: 10.1371/journal.pone.0134254.

BibTeX

@article{mcdonnell2015fast,
  title     = {{Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm}},
  author    = {McDonnell, Mark D. and Tissera, Migel D. and Vladusich, Tony and André, van Schaik and Tapson, Jonathan C.},
  journal   = {PLoS ONE},
  year      = {2015},
  volume    = {10},
  number    = {8},
  pages     = {e0134254},
  doi       = {10.1371/journal.pone.0134254},
  url       = {https://doi.org/10.1371/journal.pone.0134254}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
20161414
20171010
20181111
20191616
202066
202199
202211
202366
202433
202544

Its field-weighted citation impact is 9.57: it has been cited 9.57 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and ELM

  • handwritten digit recognition
  • extreme learning machine
  • shallow neural networks
  • single hidden layer neural network
  • MNIST
  • backpropagation
  • image distortion
  • rapid training

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

McDonnell, M. D., Tissera, M. D., Vladusich, T., André, V. S., & Tapson, J. C. (2015). Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm. PLoS ONE, 10(8), e0134254. https://doi.org/10.1371/journal.pone.0134254

How many times has this paper been cited?

89 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at PLoS ONE.

Who wrote this paper?

Mark D. McDonnell, Migel D. Tissera, Tony Vladusich, van Schaik André, Jonathan C. Tapson.

What is the DOI of this paper?

10.1371/journal.pone.0134254. The permanent link is https://doi.org/10.1371/journal.pone.0134254.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.