Skip to main content
SpringerLink
Log in

A Fast Self-Organizing Map Algorithm for Handwritten Digit Recognition

  • Conference paper
  • First Online:
Multimedia and Ubiquitous Engineering

Part of the book series: Lecture Notes in Electrical Engineering ((LNEE,volume 240))

Abstract

This paper presents a fast version of the self-organizing map (SOM) algorithm, which simplifies the weight distance calculation, the learning rate function and the neighborhood function by removing complex computations. Simplification accelerates the training process in software simulation and is applied in the field of handwritten digit recognition. According to the evaluation results of the software prototype, a 15–20 % speed-up in the runtime is obtained compared with the conventional SOM. Furthermore, the fast SOM accelerator can recognize over 81 % of handwritten digit test samples correctly, which is slightly worse than the conventional SOM, but much better than other simplified SOM methods.

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 259.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 329.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 329.99
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

References

  1. Kohonen T (1990) The self-organizing map. Proc IEEE 78(1):1464–1480

    Article  Google Scholar 

  2. Kohonen T, Kaski S, Lagus K et al (2000) Self organization of a massive document collection. IEEE Trans Neural Netw 11(3):574–585

    Article  Google Scholar 

  3. Silven O, Niskanen M, Kauppinen H (2003) Wood inspection with non-supervised clustering. Mach Vis Appl 3:275–285

    Article  Google Scholar 

  4. Mu-Chun S, Hsiao-Te C (2000) Fast self-organizing feature map algorithm. IEEE Trans Neural Netw 11(3):721–732

    Article  Google Scholar 

  5. Nordström T (1992) Designing parallel computers for self organizing maps. In: Fourth Swedish workshop on computer system architecture

    Google Scholar 

  6. Lobo VJ, Bandeira N, Moura-Pires F (1998) Distributed Kohonen networks for passive sonar based classification. In: International conference on multisource-multisensor information fusion, Las Vegas

    Google Scholar 

  7. Yaohua Y, Damminda A (2006) Batch implementation of growing self-organizing map. In: International conference on computational intelligence for modelling control and automation, and international conference on intelligent agents, web technologies and internet commerce

    Google Scholar 

  8. Pena J, Vanegas M (2006) Digital hardware architecture of Kohonen’s self organizing feature maps with exponential neighboring function. In: IEEE international conference on reconfigurable computing and FPGA

    Google Scholar 

  9. Agundis R, Girones G, Palero C, Carmona D (2008) A mixed hardware/software SOFM training system. Computaciny Sistemas 4:349–356

    Google Scholar 

  10. Porrmann M, Witkowski U, Ruckert U (2006) Implementation of self-organizing feature maps in reconfigurable hardware. In: FPGA implementations of neural networks. Springer, Heidelberg, pp 247–269

    Google Scholar 

  11. LeCun Y, Cortes C, The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/

Download references

Author information

Authors and Affiliations

  1. Institute of VLSI Design, Zhejiang University, Hangzhou, People’s Republic of China

    Yimu Wang, Yun Pan & Xiaolang Yan

  2. EDM, Hasselt University, Diepenbeek, Belgium

    Alexander Peyls & Luc Claesen

Authors
  1. Yimu Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Alexander Peyls
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yun Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Luc Claesen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiaolang Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yimu Wang .

Editor information

Editors and Affiliations

  1. Department of Computer Science and Engineering, Seoul University of Science & and Technology (SeoulTech), Seoul, Korea, Republic of (South Korea)

    James J. (Jong Hyuk) Park

  2. Dept of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong SAR

    Joseph Kee-Yin Ng

  3. Humanitas College, Kyung Hee University, Seoul, Korea, Republic of (South Korea)

    Hwa-Young Jeong

  4. School of Computer Science and Software Engineering, Monash University, Clayton, Victoria, Australia

    Borgy Waluyo

Rights and permissions

Reprints and permissions

Copyright information

© 2013 Springer Science+Business Media Dordrecht(Outside the USA)

About this paper

Cite this paper

Wang, Y., Peyls, A., Pan, Y., Claesen, L., Yan, X. (2013). A Fast Self-Organizing Map Algorithm for Handwritten Digit Recognition. In: Park, J., Ng, JY., Jeong, HY., Waluyo, B. (eds) Multimedia and Ubiquitous Engineering. Lecture Notes in Electrical Engineering, vol 240. Springer, Dordrecht. https://doi.org/10.1007/978-94-007-6738-6_23

Download citation

  • DOI: https://doi.org/10.1007/978-94-007-6738-6_23

  • Published:

  • Publisher Name: Springer, Dordrecht

  • Print ISBN: 978-94-007-6737-9

  • Online ISBN: 978-94-007-6738-6

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation