Abstract
In this paper we want to present computer simulations of an algorithm of pattern recognition and associative memory, which was introduced by Haken [1] at the International Symposium at Schloß Elmau, Bavaria in 1987. This was the first specific formulation of a synergetic system that exhibited the analogy between pattern formation and pattern recognition that Haken suggested in 1979 [2]. The crucial point is that the ability of a system to form patterns is strongly related to its ability to recognize patterns or to act as an associative memory. While these basic ideas are discussed in the article of Haken (cf. these proceedings), we shall focus our attention on explicit simulations, and on a discussion of possible generalizations of this approach [3,4]. We shall proceed as follows: In Section 2 we introduce the mathematical assumptions that are nessecary, and show how an associative memory can be realized by a synergetic system [5,6]. In Section 3 we shall reduce the degrees of freedom of the system by introducing order parameters describing the interaction between the macroscopic states of the system. Then in the Sections 4 and 5 generalizations of our approach are discussed. We show that the approach can be formulated in a translationally invariant form which will lead us to the ability to decompose complex patterns or scenes [7]. In Section 5, a further generalization with respect to rotation and scaling is introduced, by use of the complex logarithmic map which also exists in the visual systems of mammals [8,9] as the connection between the retina and the visual cortex.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Haken, H.: Synergetic Computers for Pattern Recognition and Associative Memory. In: Computional Systems, Natural and Artificial,H. Haken, Ed., Springer, Berlin, (1987)
Haken, H.: Pattern Formation and Pattern Recognition - An Attempt at a Synthesis. In: Pattern Formation by Dynamical Systems and Pattern Recognition, H. Haken, Ed., Springer, Berlin, (1979)
Haken, H.: Nonequilibrium Phase Transitions in Pattern Recognition and Associative Memory. Z. Phys. B - Condensed Matter 70, (1988), 121–123
Fuchs, A. and Haken, H: Nonequilibrium phase transitions in pattern recognition and associative memory. Numerical results.Z. Phys. B - Condensed Matter 73, (1988), in press
Fuchs, A. and Haken, H.: Pattern Recognition and Associative Memory as Dynamical Process in Nonlinear Systems. Submitted to: IEEE International Conference on Neural Nets, (1988)
Haken, H. and Fuchs, A.: Pattern Formation and Pattern Recognition as Dual Processes. In: Dynamic Patterns in Complex Systems, J.A.S. Kelso, A.J. Mandell, M.F. Schlesinger, Ed., World Scientific, Singapore, (1988)
Fuchs, A. and Haken, H.: Pattern Recognition and Associative Memory as Dynamical Process in Synergetic Systems. Translational Invariance, Selective Attention, and Decomposition of Scenes. To be published in Biol. Cybern., (1988)
Fischer, B.: Overlap of receptive field centers and representation of the visual field in the cat’s optic tract. Vision Res. 13, (1988), 2113–2120
Schwarz, E.L.: Spatial mapping in the primate sensory projection: analytic structure and relevance to perception. Biol. Cybern. 25, (1977), 181–194
Haken, H.: Synergetics, an Introduction, 3rd. ed., Springer, Berlin, (1983)
]Haken, H.: Advanced Synergetics, 2nd. corr. printing, Springer, Berlin, (1987)
Altes, R.A.: The Fourier-Mellin transform and mammalian hearing. J. Acoust. Soc. Am. 63, (1978), 174–183
Reitboeck, H. J. and Altmann, J.: A Model for Size-and Rotation-Invariant Pattern Processing in the Visual System. Biol. Cybern., 51, (1984), 113–121
Braccini, C. et. al.: A Model of the Early Stage of Human Visual System: Functional and Topological Transformations Performed in the Peripherical Visual Field. Biol. Cybern., 44, (1982), 47–58
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1988 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fuchs, A., Haken, H. (1988). Computer Simulations of Pattern Recognition as a Dynamical Process of a Synergetic System. In: Haken, H. (eds) Neural and Synergetic Computers. Springer Series in Synergetics, vol 42. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-74119-7_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-74119-7_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-74121-0
Online ISBN: 978-3-642-74119-7
eBook Packages: Springer Book Archive