Abstract
Artificial Neural Networks (ANNs) are large collections of interacting entities. Certain conditions of behavior and of nonlinear coupling between the entities enable self-organization of the system with emergent properties of associative memory, abstraction and generalization. Therefore, it should not be surprising that the mathematical tools of irreversible thermodynamics and evolution are very relevant and useful in the analysis of these interesting "computational networks". The behavioral resemblance between ANNs and certain dynamical physical systems is not coincidental.
The analysis of ANNs may be viewed principally as a statistical mechanics problem. Formidable as it may seem to some students the prospect of having to learn statistical mechanics, it becomes almost a thing of necessity to anyone who attempts to analyse the behavior of "many-component, massively connected" systems, whether it is called that or not. In this brief discourse, we use statistical mechanics (mostly implicitly) only as a means to see things in a unified perspective.
We first present a distilled argument about the emerging properties of self-organization in certain kinds of cooperative (synergetic) physical systems. Subsequently, we present the essential properties of ANNs, as we know them now, with an eye on the current theoretical and technological problems which stand in the way of wide-spread commercialization of ANNs, and of cooperative computing machines in general.
Preview
Unable to display preview. Download preview PDF.
References
Feynman, R.P.(1982), "Simulating Physics with Computers", Intl. J. Theor. Phys., 21, 6/7:467–489.
Haken, H.(1988), Information and Self-Organization, Springer Ser. Synergetics, vol.40, Springer.
Hopfield, J.J.(1982), "Neural Networks and Physical Systems with Emergent Collective Computational Abilities", Proc. of the National Academy of Sciences, USA, 79, 2554–2558
Ligomenides, P. A.(1982), "Symbolic Space Determinations on Physical Limitations", Int'l, J. of Theoretical Phys. 1 (12), 973–978.
Ligomenides, P. A.(1986), "On-Line Recognition and Labeling of Behavioral Modalities", Proc. of the Int'l IEEE Conf. on Systems, Man and Cybernetics, Atlanta, GA, October 14–17.
Ligomenides, P. A(1987)., "Modeling Uncertainty in Human Perception", in Lecture Notes in Computer Science: Uncertainty in Knowledge-Based Systems, R.R. Yager and B. Bouchon (Eds), Springer-Verlag.
Ligomenides, P. A.(1987), "Procedural and Progressive Formal Models of Human Perception", Proc. of the IEEE Conf. on Systems, Man and Cybernetics, Alexandria, VA, October 20–23.
Ligomenides, P. A.(1987), "Resemblance, Fuzziness and Uncertainty in Experiential Knowledge Engineering", Proc. of the CAFSFM Int'l Symp. on Fuzzy Sys. and Knowl. Engin., Guangzhou, China, July 10–16.
Ligomenides, P. A.(1988), "Intelligent Robotics: Recognition and Reasoning", (Plenary session paper) Proc. of the IEEE Workshop on Languages for Automation, University of Maryland, pp 44–59, August 29–31.
Ligomenides, P. A.(1990), "On-Line Visual Prosthesis for a Decision Maker", Proc. of SPIE-OPTCON'90 Conf. on Advances in Intelligent Robotic Systems, Boston, Mass., Nov. 2–4.
Ligomenides, P. A. (1991), "Induction and Uncertainty in Synergetic Computing Systems", in Uncertainty Management and Analysis, B.Z.Ayyub et al (Eds), North Holland.
Nicolis, G. and I. Prigogine, (1977), Self-Organization in Nonequilibrium Systems, Wiley, New York.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ligomenides, P.A. (1991). Cooperative computing and neural networks. In: Prieto, A. (eds) Artificial Neural Networks. IWANN 1991. Lecture Notes in Computer Science, vol 540. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0035871
Download citation
DOI: https://doi.org/10.1007/BFb0035871
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54537-8
Online ISBN: 978-3-540-38460-1
eBook Packages: Springer Book Archive