Abstract
A highly flexible environment has been developed based on the object-oriented paradigm for modelling artificial neural networks (ANNs). This paper propose a hierarchy of classes that models ANN. The design of the hierarchy is characterized by a high degree of modularity, based on parametrizable data structures and autonomous modules. Composition rules of structures and methods enable to build, step by step, more complex structures from simple ones previously defined. One of the most relevant benefits obtained from using an object-oriented approach is related with the definition of multi-networks. URANO (Universe of ANN Object oriented) is a powerful software tool developed using the C++ programming language for building and using prototypes of ANNs in which inherited mechanism can be used for building new ANNs from already existing ones. It is easy to work with and its effectiveness and efficiency have been proven by applications.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Gael de la Croix, Catherine Molinoux, Benol Derot. “The N programming Language”, NATO ASI Series, Vol. F68 Neurocomputing. pp. 89–92, Springer Verlag Berlin Heidelberg 1990.
Mark Mullin. “Object Oriented Program Design.”, Ed. Addisson Wesley, 1990.
Gregory L. Heilemen, Michael Georgiopoulos, y William D. Roome. “A General Framework for Concurrent Simulation of Neural Network Models”. IEEE Transactions on Sotfware Engineering. Vol 18, No. 7, July 1992. pp. 551–562.
J.F. Aldana, E. Pimentel, J.M. Troya. “Modelado de Redes neuronales mediante un lenguaje Lógico concurrente orientado a objeto”. Actas de las Jornadas sobre programación declaraliva. pp. 561–570. Torremolinos, Málaga, 1991.
Troya, Aldana. 91 “Extending an Object-Oriented Concurrent Logic Language for Neural Networks Simulation”. IWANN'91. LNCS no. 540, pp. 235–243, Springer Verlag 1991.
L. Fuentes, J.F. Aldana, J.M. Troya. “Modelado Redes Neuronales mediante un lenguaje lógico concurrente orientado a objeto” Informe Técnico. Dpto de Lenguajes y Ciencias de la Computación. Universidad de Málaga. 1992.
Scott Robert Ladd. “C++ Techniques & Applications”, Prentice Hall.
Darkui Shouren Hu. “An Object Oriented Neural Network Language”, CH 3065 IEEE pp. 1606–1611, 1991.
Leslie S. Smith. “A Framework for Neural Net Specification”. IEEE Transactions on Sotfware Engineering. Vol 18. No. 7, July 1992. pp. 601–612.
Gregory L. Heileman, Harold K. Brown. “Simulation of Artificial Neural Networks Models Using an Object-Oriented Software Paradigm”, pp. 133–136.
L. Fuentes, J.F. Aldana, J.M. Troya. “Modclado dc Redes Neuronales con URANO”. Informe Técnico. Dpto. de Lenguajes y Ciencias de la Computación. Universidad de Málaga. 1992.
V. Cruz, G. Cristobal, T. Michaux, S. Barquin. “Distortion Invariant Image Recognition by Madaline and BackPropagation Learning Multi-Networks”. NATO ASI Series, Vol. F68 Neurocomputing. pp. 337–342, Springer Verlag Berlin Heidelberg 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fuentes, L., Aldana, J.F., Troya, J.M. (1993). Urano: An object-oriented artificial neural network simulation tool. In: Mira, J., Cabestany, J., Prieto, A. (eds) New Trends in Neural Computation. IWANN 1993. Lecture Notes in Computer Science, vol 686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56798-4_174
Download citation
DOI: https://doi.org/10.1007/3-540-56798-4_174
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56798-1
Online ISBN: 978-3-540-47741-9
eBook Packages: Springer Book Archive