Synaptic modulation based artificial neural networks

  • R. J. Duro
  • J. Santos
  • A. Gómez
Part of the Lecture Notes in Computer Science book series (LNCS, volume 930)


This work introduces complex processing neural network topologies, based on the concept of modulating neuron, which induce higher order terms by means of the modulation of the synaptic weights. These structures present the advantages of being very easy to train, adapting easily to changing contexts and offer very good generalization capabilities along all the dimensions of the problems they are trained to solve. Finally, the function each modulation level or each module performs is very clear, making it simple to extend the model to multilevel hierarchies.


Modulate Network Synaptic Weight Generalization Capability Abstraction Hierarchy Gaussian Type Function 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Giles, C. L., and Maxwell, T., Learning, Invariance, and Generalization in High-Order Neural Networks, Applied Optics, Vol. 26, No. 23, December 1987.Google Scholar
  2. [2]
    McCulloch, W. S., and Pitts, W., A Logical Calculus of the Ideas Immanent in Neural Activity, Bulletin of Mathematical Biophysics, Vol. 5, pp. 115–133, 1943.Google Scholar
  3. [3]
    Hawkins, R. D., Abrams, W.T., Carew, T.J., and Kandel, E.R., A Cellular Mechanism of Classical Conditioning in Aplysia: Activity Depedent Amplification of Presynaptic Facilitation, Science, Vol. 219, pp. 400–405, January 1983.PubMedGoogle Scholar
  4. [4]
    Silva, A. J., Stevents, C.F., Tonehawa, S., and Wang, Y. Y., Defficient Hippocampal Long Term Potentiation in α-Calcium-Calmodulin Kinase-II Mutant Mice. Science 257, No. 5067, pp 201–206, 1992.PubMedGoogle Scholar
  5. [5]
    Dehaene, S., Changeux, J., and Nadal, J., Neural Networks that Learn Temporal Sequences by Selection, Procc. Natl. Acad. Sci. USA, Vol. 84, pp. 2727–2731, May 1987.Google Scholar
  6. [6]
    Dehaene, S., and Changeux, J., Neuronal Models of Cognitive Functions, Cognition 33, pp, 63–109, 1989.PubMedGoogle Scholar
  7. [7]
    Peretto, P., and Niez, J.J., Long Term Memory Storage Capacity of Multiconnected Neural Networks, Biol. Cybern. 54, pp. 53–63, 1986.PubMedGoogle Scholar
  8. [8]
    Duro, R. J., Santos, J., and, Sarmiento, A., GENIAL, an Evolutionary Recurrent Neural Network Designer and Trainer. In Proceedings of CAST'94 (Fourth International Workshop on Computer Aided Systems Technology), Ottawa, Canada, May 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • R. J. Duro
    • 1
  • J. Santos
    • 2
  • A. Gómez
    • 2
  1. 1.Dpto. Ingeniería IndustrialUniversidad de La CoruñaSpain
  2. 2.Dpto. de ComputaciónFacultade de InformáticaSpain

Personalised recommendations