Skip to main content

Weightless Neural Networks: A Comparison Between the Discriminator and the Deterministic Adaptive RAM Network

  • Conference paper
Knowledge-Based Intelligent Information and Engineering Systems (KES 2004)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 3214))

Abstract

This paper describes recent progress and attempts to analyse a weightless neural network (WNN), known as the Deterministic Adaptive RAM Network(DARN). We obtained a reasonable classification accuracy on a variety of problems with this WNN. We also present a comparison with the WISARD Discriminator. In this paper we also analyse the storage capacity of the DARN and compare it with that of the Discriminator. This shows that the DARN has good potential for use in intelligent embedded systems applications.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight 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. Deneubourg, J.L., Goss, S., Franks, N.R., Sendova-Franks, A., Detrain, C., Chretien, L.: The Dynamics of Collective Sorting: Robot-like Ants and Ant-like Robots. In: Meyer, J.-A., Wilson, S. (eds.) Simulation of Adaptive Behaviour: From Animals to Animates, pp. 356–365. MIT Press, Massachusetts (1990)

    Google Scholar 

  2. Hoe, K.M., Lai, W.K., Tai, T.S.Y.: Homogeneous Ants for Web Document Similarity Modelling and Categorization. In: International Workshop on Ant Algorithms, Brussels Belgium, September 2002, pp. 256–261 (2002)

    Google Scholar 

  3. Lippmann, R.P.: Pattern classification using neural networks. IEEE Communication Magazine, 47–64 (January 1989)

    Google Scholar 

  4. Rumelhart, D.E., Hinton, G.E., William, R.J.: Learning internal representation by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructures of Cognition, vol. 1, MIT Press, Cambridge (1986)

    Google Scholar 

  5. Ludermir, T.B., et al.: Weightless Neural Models: A Review of Current and Past Works. Neural Computing Surveys 2, 41–60 (1999), http://www.icsi.berkeley.edu/~jagota/NCS

    Google Scholar 

  6. Kan, W.K., Aleksander, I.: A Probabilistic Logic Neuron Network for Associative Learning. In: Proc. IEEE 1st Int. Conf. on Neural Networks, San Diego, June 1987, vol. II, pp. 541–548 (1987)

    Google Scholar 

  7. Filho, E.C.D.B.C., Fairhurst, M.C., Bisset, D.L.: Adaptive Pattern Recognition using Goal Seeking Neurons. Pattern Recognition Letters 12, 131–138 (1991)

    Article  Google Scholar 

  8. Bowmaker, R.G., Coghill, G.G.: Improved Recognition Capabilities for Goal Seeking Neuron. Electronics Letters 28(3), 220–221 (1992)

    Article  Google Scholar 

  9. Coghill, G., Lai, W.K.: The Use of Weightless Neural Networks for the Extraction of Feature Information from Web Documents for Taxonomy Construction. In: Proceedings of the International Conference on Robotics, Vision, Information & Signal Processing, Penang, Malaysia, January 2003, pp. 257–260 (2003)

    Google Scholar 

  10. UCI Repository of Machine Learning Databases, http://www.ics.uci.edu/~mlearn/MLRepository.html

  11. Fisher, R.A.: The Use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics 7, Part II, 179–188 (1936)

    Google Scholar 

  12. Aeberhard, S., Coomans, D., de Vel, O.: The Classification Performance of RDA, Tech. Report. No. 92-01, 1992, Department of Computer Science and Department of Mathematics and Statistics, James Cook University of North Queensland (1992)

    Google Scholar 

  13. Wolberg, W.H., Mangasarian, O.L.: Multisurface method of pattern separation for medical diagnosis applied to breast cancer cytology. In: Proceedings of the National Academy of Sciences, U.S.A., December 1990, vol. 87, pp. 9193–9196 (1990)

    Google Scholar 

  14. Smith, J.W., Everhart, J.E., Knowler, W.C., Johannes, R.S.: Using the ADAP learning algorithm to forecast the onset of diabetes mellitus. In: Proceedings of the Symposium on Computer Applications and Medical Care, pp. 261–265. IEEE Computer Society Press, Los Alamitos (1988)

    Google Scholar 

  15. Stone, M.: Cross-validatory Choice and Assessment of Statistical Predictions. Journal of the Royal Statistical Society, Series B 36, 111–147 (1974)

    MATH  Google Scholar 

  16. Penny, W., Stonham, T.J.: Storage Capacity of Multilayer Boolean neural networks. Electronics letters 29, 1340–1341 (1993)

    Article  Google Scholar 

  17. Rohwer, R., Morciniec, M.: The theoretical and experimental status of the n-tuple classifier. Neural Networks 11(1), 1–14 (1998)

    Article  MATH  Google Scholar 

  18. Aleksander, I., Thomas, W., Bowden, P.: WISARD, a radical step forward in image recognition. Sensor Review, 120–124 (1984)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2004 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Yee, P., Coghill, G. (2004). Weightless Neural Networks: A Comparison Between the Discriminator and the Deterministic Adaptive RAM Network. In: Negoita, M.G., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2004. Lecture Notes in Computer Science(), vol 3214. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30133-2_41

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-30133-2_41

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-23206-3

  • Online ISBN: 978-3-540-30133-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics