Skip to main content
SpringerLink
Log in

Bidirectional Activation-based Neural Network Learning Algorithm

  • Conference paper
Artificial Neural Networks and Machine Learning – ICANN 2013 (ICANN 2013)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 8131))

Included in the following conference series:

Abstract

We present a model of a bidirectional three-layer neural network with sigmoidal units, which can be trained to learn arbitrary mappings. We introduce a bidirectional activation-based learning algorithm (BAL), inspired by O’Reilly’s supervised Generalized Recirculation (GeneRec) algorithm that has been designed as a biologically plausible alternative to standard error backpropagation. BAL shares several features with GeneRec, but differs from it by being completely bidirectional regarding the activation propagation and the weight updates. In pilot experiments, we test the learning properties of BAL using three artificial data sets with binary patterns of increasing complexity.

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 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. Almeida, L.: A learning rule for asynchronous perceptrons with feedback in a combinatorial environment. In: Proceedings of the IEEE First International Conference on Neural Networks, San Diego, CA (1987)

    Google Scholar 

  2. Hinton, G.E., McClelland, J.L.: Learning representations by recirculation. In: Neural Information Processing Systems, pp. 358–366. American Institute of Physics, New York (1988)

    Google Scholar 

  3. O’Reilly, R.: The Leabra model of neural interactions and learning in the neocortex. Ph.D. thesis, Carnegie Mellon University (1996)

    Google Scholar 

  4. O’Reilly, R.: Biologically plausible error-driven learning using local activation differences: The generalized recirculation algorithm. Neural Computation 8(5), 895–938 (1996)

    Article  MathSciNet  Google Scholar 

  5. O’Reilly, R., Munakata, Y., Frank, M., Hazy, T.: Computational Cognitive Neuroscience, 2nd edn. Wiki Book (2012)

    Google Scholar 

  6. Pineda, F.: Generalization of back-propagation to recurrent neural networks. Physics Review Letters 59, 2229–2232 (1987)

    Article  MathSciNet  Google Scholar 

  7. Rebrová, K., Pecháč, M., Farkaš, I.: Towards a robotic model of the mirror neuron system. In: The 3rd Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (2013)

    Google Scholar 

  8. Rumelhart, D., Hinton, G., Williams, R.: Learning internal representations by error propagation, vol. 1, pp. 318–362. MIT Press, Cambridge (1986)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Mathematics, Physics and Informatics, Comenius University in Bratislava, Slovakia

    Igor Farkaš & Kristína Rebrová

Authors
  1. Igor Farkaš
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kristína Rebrová
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Faculty Automation,, Technical University of Sofia, 8 St. Kl. Ohridski Blvd., 1000, Sofia, Bulgaria

    Valeri Mladenov

  2. Institute of Information and Communication Technologies, Bulgarian Academy of Sciences, Acad. G. Bonchev str. bl.25A, 1113, Sofia, Bulgaria

    Petia Koprinkova-Hristova

  3. Institute of Neural Information Processing, University of Ulm, 89075, Ulm, Germany

    Günther Palm

  4. Quartier UNIL-Dorigny, Bâtiment Internef, Université de Lausanne, 1015, Lausanne, Switzerland

    Alessandro E. P. Villa

  5. Department of Computer Science, University of Milano, Via Comelico, 39, 20135, Milano, Italy

    Bruno Appollini

  6. Knowledge Engineering, School of Computing and Mathematical Sciences, Auckland University of Technology, 120 Mayoral Drive, 3rd floor, 1010, Auckland, New Zealand

    Nikola Kasabov

Rights and permissions

Reprints and permissions

Copyright information

© 2013 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Farkaš, I., Rebrová, K. (2013). Bidirectional Activation-based Neural Network Learning Algorithm. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds) Artificial Neural Networks and Machine Learning – ICANN 2013. ICANN 2013. Lecture Notes in Computer Science, vol 8131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40728-4_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-40728-4_20

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-40727-7

  • Online ISBN: 978-3-642-40728-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation