Bases of a cast system for formal neural nets

  • C. P. Suárez-Araujo
  • R. Moreno-DíazJr.
Knowledge Based Systems, Artificial Perception And CAST
Part of the Lecture Notes in Computer Science book series (LNCS, volume 410)


Formal neural nets considered here are McCulloch-Pitts type with interactions of afferents, that is formal neurons capable of computing any logical function of the inputs.

The main problem considered by the CAST system is that of network synthesis from the state transition matrix of a net.

The system consists of three blocks: an input block, which accepts state transition matrix specification and provides the number of neurons and the logical functions to be performed by them.

A second block provides, from the function of each neuron, the corresponding neural diagram, including the interaction of afferents. This interaction can be optimized to maximum reliability against changes in threshold.

The third block generates the whole net including the effect of presynaptic and postsynaptic excitations and inhibitions.

The system allows for quick investigation on the effect of synaptic changes upon global behaviour (i.e. state transition matrix) when, for example, the network is subjected to learning changes in pre- and postsynapses.

Efferent interaction, which are necessary for arbitrary probabilistic nets, are not considered in the system, for the moment.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. -.
    Blum, M. (1961): "Properties of a Neuron With Many Inputs". In: Principles of Self Organization. (Von Forester and Zopf, Eds.) McMillan Pergamon. Oxford New York. PP. 95–119.Google Scholar
  2. -.
    McCulloch, W.S. (1958): "Agatha Fiche: of Nervous Nets the Lucky Reckoners". Prooc. Symp. Held at the National Physical Laboratory, London. Vol. II, No. 10. PP. 613–625.Google Scholar
  3. -.
    Monroy Benítez, J (1982): "Una Reformulación de la Teoría de Neuronas Formales". Tesis de licenciatura. Universidad Nacional Autónoma de México, Facultad de Ciencias.Google Scholar
  4. -.
    Moreno-Díaz, R. (1980): "Teoría de Redes Neuronales". (Cibernética, Aspectos y tendencias Actuales). Real Academia de Ciencias Exactas, Físicas y Naturales.Google Scholar
  5. -.
    Moreno-Díaz,R. McCulloch,W.S. (1969): "Circularities in Nets and the Concept of Functional Matrices". Biocybernetics of the Central Nervous System. Proctor L. (ed.) Ma U.S.A. Little and Brown.Google Scholar
  6. -.
    Moreno-Díaz,R. McCulloch, W.S. (1968): "Redes Neuronales con Realimentación y Matrices Funcionales". Automática 1, 1.Google Scholar
  7. -.
    Moreno-Díaz,R., Mira Mira,J., Roy Yarza,A. (1972): "Realización de Redes No-determinísticas". Automática 11, V.Google Scholar
  8. -.
    Pichler, F (1988): "CAST-Finite State Machine II and CAST-Application Examples". Lectures in the University of the Las Palmas de G.C.Google Scholar
  9. -.
    Von Neuman, J. (1956): "Probabilistic Logic and the Synthesis of Reliable Organisms from Unreliable Components". In: Automatic Studies. (Shannon and McCarthy eds.) Princenton University Press, New Jersey.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • C. P. Suárez-Araujo
    • 1
  • R. Moreno-DíazJr.
    • 1
  1. 1.Department of Computer Sciences and SystemsUniversity of Las Palmas of Gran CanariaLas PalmasSpain

Personalised recommendations