Skip to main content

An Orthogonal Neural Network with Guaranted Recall by Iterative Filters and Its Application to Texture Discrimination

  • Conference paper
Artificial Neural Nets and Genetic Algorithms

Abstract

It is presented an orthogonal neural network which uses parallel iterative filters in its hidden layer. Orthogonality gives a high storage capacity of the network and its iterative filters get an accurate response. Also, this filters are implemented by a parallel process for getting a quick convergence time. As a simple example of application, we use it to learn several natural textures and its classification.

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. Chung-Ming Wu and Yung-Chang Chen: Multi-Threshold vector for texture analysis and its application to liver tissue classification. Pattern recognition Vol. 26 pg. 137–144, 1993.

    Article  Google Scholar 

  2. Hopfield J. J.:Neural Networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Science, vol 79, pg. 2554–2558. 1984.

    Article  MathSciNet  Google Scholar 

  3. Hopfield J.J.:Neural networks with graded response have collective Computational properties like those of two-state Neurons. Proceedings of the National Academy of Science, vol 81, pg. 3088–3092. 1984.

    Google Scholar 

  4. Ibarra Picó, F. & García Chamizo, J. M.: Memorias Asociativas Bidireccionales Orthonormalizadas. V Conferencia de la Asociación Española Para la Inteligencia Artificial. Actas AEPIA. Noviembre 1993.

    Google Scholar 

  5. Ibarra Picó, F. & García Chamizo, J. M. Memorias Asociativas Bidireccionales Orthonormalizadas. Revista Novática. 1994.

    Google Scholar 

  6. Ibarra Picó, F. & García Chamizo, J. M.: A Generalized Bidirectional Associative Memory with a Hidden Orthogonal Layer. ICANN’94, Sorrento, May 1994.

    Google Scholar 

  7. Kosko, B.: Bidirectional Associative Memories. IEEE Tans, on Systems, Man & Cybernetics, vol 18, n 1. 1988.

    Google Scholar 

  8. Kosko, B.: Competitive adaptative bidirectional associative memories. Procedings of the IEEE first International Conference on Neural Networks,M. Cardill and C. Butter vol 2. pp 759–66. 1988.

    Google Scholar 

  9. McLean G.F.: Vector Quantization for Texture Gasification. IEEE Transactions on Systems man and Cybernetics vol. 23 No. 3. 1993.

    Google Scholar 

  10. Pao You-Han: Adaptative Pattern Recognition and Neural Networks. Addison-Wesley Publishing Company, Inc. pg 144–148. 1989.

    Google Scholar 

  11. Wang, Cruz F.J., Mulligan: On Multiple Training for Bidirectional Associative Memory. IEEE Tans, on Neural Networks, 1 (5) pg 275–276. 1990.

    Google Scholar 

  12. Wang, Cruz F.J., Mulligan. Two Coding Strategies for Bidirectional Associative Memory. IEEE Tans, on Neural Networks, pg 81–92. 1990.

    Google Scholar 

  13. Wang, Cruz F.J., Mulligan: “Guaranted Recall of All training Pairs for Bidirectional Associative Memory”. IEEE Tans, on Neural Networks, 2 (6) pg 559–567. 1991.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

Copyright information

© 1995 Springer-Verlag/Wien

About this paper

Cite this paper

Ibarra-Picó, F., García-Chamizo, J.M., Satorre-Cuerda, R. (1995). An Orthogonal Neural Network with Guaranted Recall by Iterative Filters and Its Application to Texture Discrimination. In: Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-7535-4_50

Download citation

  • DOI: https://doi.org/10.1007/978-3-7091-7535-4_50

  • Publisher Name: Springer, Vienna

  • Print ISBN: 978-3-211-82692-8

  • Online ISBN: 978-3-7091-7535-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics