Abstract
We introduce a neural network architecture based on Smolensky’s Harmony Theory in order to solve a particular form of Binding Problem in a visual scene containing 4 subpatterns. The network performance is studied through computer simulations. The results obtained evidence how Harmony Theory can be used to solve Binding Problem, but its performance, even if significatively greater than chance level, is still too low.
This is a preview of subscription content, log in via an institution to check access.
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
J. Fodor, E. Lepore. The red herring and the pet fish: why concepts still can’t be prototypes. Cognition, 58:253–270, 1996.
J.E. Hummel, I Biederman. Dynamic binding in a neural network for shape recognition. Psychological Review, 99:480–517, 1992.
S. Kirpatrick, C.D. Gelatt, M.P. Vecchi. Optimization by simulated annealing. Science, 220:671–680, 1983.
T. Kohonen. Selforganization and associative memory. Springer, Berlin-Heidelberg-New York, 1984.
E. Pessa, M.P. Penna. Neural architectures able to give a description of 2-dimensional visual scenes. In IAPRVA 98-Artificial Intelligence and Pattern Recognition Techniques for Computer Vision, pages 206–211, Ferrara, Avril 1998.
J.L. Mc Clelland, D.E. Rumelhart, editors, Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press, Cambridge MA, 1986.
P. Smolensky. Information Processing in Dynamical Systems: Foundations of Harmony Theory. In J.L. Mc Clelland, D.E. Rumelhart, editors, Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. I, pages 154–281, MIT Press, Cambridge MA, 1986.
T. Tambouratzis. A simulated annealing artificial neural network implementation of the n-queens problem. International Journal of Intelligent Systems, 12: 739–751, 1997.
P. Tse, D. Wang, D. Atherton. Harmony Theory yields robust machine fault diagnostic system based on Learning Vector Quantization Classifier. Engineering Applications of Artificial Intelligence, 9: 487–498, 1996.
P.H. Winston. The Psychology of Computer Vision, Mc Graw-Hill, New York, 1975.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag London Limited
About this paper
Cite this paper
Pessa, E., Penna, M.P. (1999). Harmony Theory and Binding Problem. In: Marinaro, M., Tagliaferri, R. (eds) Neural Nets WIRN Vietri-99. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-0877-1_12
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0877-1_12
Publisher Name: Springer, London
Print ISBN: 978-1-4471-1226-6
Online ISBN: 978-1-4471-0877-1
eBook Packages: Springer Book Archive