Abstract
To explain the multistable perception in “reversible figures”, an artificial perceptron neural network model is proposed. The networks are composed by a shifting invariant smart eye preprocessing unit, a depth processing unit and the main brain computing unit. The shift invariant preprocessing unit could be achieved by wavelet transform optical filters (Sheng et al., 1993) or fixed artificial neural networks (Widrow & Winter, 1988). The depths processing unit is constructed by two McCulloch-Pitts neurons with time-dependent threshold, which is updated by modified Haken’s time-dependent attention parameters dynamics. The main brain computing network is a revised back error propagation network. Following Haken’s (1991) description, we adopt Stadler’s connectionist approach. We use a polynomial energy function, e.g., £4 field, for the performance measure replacing the least mean square energy. The training of the computing network follows a standard supervised delta learning rule of interconnected weights. The test of “reversible figures” is subsequently controlled by the phase transition tuning parameter driven bottom up from test image data. The effects of the tuning parameter are illustrated. And the modeling of multistable perception is discussed. We demonstrate that the brain computing networks trained with the new energy function generally perform better in training speed and classification of patterns than the standard back error propagation networks trained by the least mean square energy.
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
Ditzinger, A., Fuchs, T. & Haken, H. (1992): Synergetic Approach to Phenomena of Perception in Neural and Artificial Systems. Berlin: Springer.
Freeman, J.A. & Skapura, D.M. (1991): Neural Networks: Algorithms, Applications, and Programming Techniques. Addison-Wesley Publishing Company, Massachusetts.
Grady, D. (1993): The vision thing: Mainly in the brain. Discover, 57–66, June.
Grossberg, S. & Wyse, L. (1991): A neural network architecture for figure-ground separation of connected scenic figures. Neural Networks 4, 723–742.
Haken, H. (1991): Synergetic Computers and Cognition: A Top-Down Approach to Neural Networks. Berlin: Springer.
Intrator, N. & Cooper, L.N. (1992): Objective function formulation of the BCM theory of visual cortical plasticity: Statistical connection, stability conditions. Neural Networks 5, 3–17.
Rumelhart, D.R. & MacClelland, J.L., (1986): Parallel Distributed Processing: Exploration in the Microstructure of Cognition. MIT Press.
Sakai, K., Katayama, T., Wada, S. & Oiwa, K. (1993): Perspective reversal caused by chaotic switching in PDP schema model. ICNN.
Sheng, Y., Roberg, D., Szu, H. & Lu, T. (1993): Optical wavelet matched filters for shift-invariant pattern recognition. Optics Letters 18, No. 4.
Szu, H.H. &, Telfer, B. (1991): Minimum misclassification error performance measure for layered networks of artificial fuzzy neurons. IJCNN-91 Seattle.
Wagner, K. & Psaltis, D. (1987): Multiple layer optical learning network. Applied Optics 26, 25061–25076.
Werbos, P. (1974): Beyond regression New tools for prediction and analysis in the behavioral sciences. Ph.D thesis. Harvard University.
Widrow, B. & Winter, R. (1988): Neural nets for adaptive filtering and adaptive pattern recognition. Computer, March
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Szu, H.H., Lu, F., Landa, J.S. (1995). Artificial Neural Networks and Haken’s Synergetic Computer: A Hybrid Approach for Solving Bistable Reversible Figures. In: Kruse, P., Stadler, M. (eds) Ambiguity in Mind and Nature. Springer Series in Synergetics, vol 64. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-78411-8_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-78411-8_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-78413-2
Online ISBN: 978-3-642-78411-8
eBook Packages: Springer Book Archive