Skip to main content
SpringerLink
Log in

Deep Extreme Learning Machines for Classification

  • Conference paper
Proceedings of ELM-2014 Volume 1

Part of the book series: Proceedings in Adaptation, Learning and Optimization ((PALO,volume 3))

Abstract

We present a method for synthesising deep neural networks using Extreme Learning Machines (ELMs) as a stack of supervised autoencoders. We show that the network achieves comparable performance to an ELM with a single hidden layer with a size equal to the total number of hidden-layer neurons in the deep network. The main advantage of our method is in its significantly reduced network training time and memory usage. These favourable properties suggest that our method can be applied to a resource-constrained hardware implementation to increase the network performance.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 219.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Furber, S.B., Galluppi, F., Temple, S., Plana, L.A.: The SpiNNaker Project. Proceedings of the IEEE 102, 652–665 (2014)

    Article  Google Scholar 

  2. Benjamin, B.V., Gao, P., McQuinn, E., Choudhary, S., Chandrasekaran, A.R., Bussat, J.-M., Alvarez-Icaza, R., Arthur, J.V., Merolla, P.A., Boahen, K.: Neurogrid: A mixed analog-digital multi chip system for large-scale neural simulations. Proceedings of the IEEE 102, 699–716 (2014)

    Article  Google Scholar 

  3. Eliasmith, C., Anderson, C.H.: Neural Engineering: Computation, Representation, and Dynamics in Neurobiological Systems. The MIT Press (2004)

    Google Scholar 

  4. Huang, G.-B., Wang, D.H., Lan, Y.: Extreme Learning Machines: A Survey. International Journal of Machine Learning and Cybernetics 2, 107–122 (2011)

    Article  Google Scholar 

  5. Tapson, J., van Schaik, A.: Learning the pseudoinverse solution to network weights. Neural Networks 45, 94–100 (2013)

    Article  MATH  Google Scholar 

  6. Huang, G.-B., Zhu, Q.-Y., Siew, C.-K.: Extreme Learning Machine: Theory and applications. Neurocomputing 70, 489–501 (2006)

    Article  Google Scholar 

  7. Penrose, R.: A generalized inverse for matrices. Mathematical Proceedings of the Cambidge Philosophical Society 51, 406–413 (1955)

    Article  MATH  MathSciNet  Google Scholar 

  8. Galluppi, F., Davies, S., Eliasmith, C., Stewart, T., Furber, S.: Real Time On-Chip Implementation of Dynamical Systems with Spiking Neurons. In: The International Joint Conference on Neural Networks IJCNN, pp. 1–8 (2012)

    Google Scholar 

  9. Kasun, L.L.C., Zhou, H., Huang, G.-B.: Representational Learning with ELMs for Big Data. IEEE Intelligent Systems 28, 31–34 (2013)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computational and Theoretical Neuroscience Laboratory, Institute for Telecommunications Research, University of South Australia, Mawson Lakes, SA, 5095, Australia

    Migel D. Tissera & Mark D. McDonnell

Authors
  1. Migel D. Tissera
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mark D. McDonnell
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Migel D. Tissera .

Editor information

Editors and Affiliations

  1. Institute of Information and Control, Hangzhou Dianzi University, Zhejiang, China

    Jiuwen Cao

  2. School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore

    Kezhi Mao

  3. School of Computer Engineering, Nanyang Technological University, Singapore, Singapore

    Erik Cambria

  4. Faculty of Engineering and Industrial Sciences, Swinburne University of Technology, Hawthorn, Victoria, Australia

    Zhihong Man

  5. School of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea, Republic of (South Korea)

    Kar-Ann Toh

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Tissera, M.D., McDonnell, M.D. (2015). Deep Extreme Learning Machines for Classification. In: Cao, J., Mao, K., Cambria, E., Man, Z., Toh, KA. (eds) Proceedings of ELM-2014 Volume 1. Proceedings in Adaptation, Learning and Optimization, vol 3. Springer, Cham. https://doi.org/10.1007/978-3-319-14063-6_29

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-14063-6_29

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-14062-9

  • Online ISBN: 978-3-319-14063-6

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation