Abstract
The PAN system is a parallel computer architecture implementing a large associative memory, which is realized as a large network of simple artificial neurons. PAN IV realizes a 256K×4K binary memory matrix and contains 4K parallel processors. The WINA project, sponsored by the BMFT, investigates the integration of neural networks and knowledge-based systems. The elementary neural components in the hybrid WINA architecture are a neural associative memory (e.g. the PAN system) and a Kohonen map or a similar neural clustering algorithm. Our main research objectives are: (i) studying the interaction of neural and rule-based components in a prototypical hybrid system, (ii) developing new designs for special hardware for parallel processing in all components of the system, (iii) building an application-oriented information retrieval system based on the PAN architecture.
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
Amit, D.J., Gutfreund, H., Sompolinsky, H.: Scientific American. 1989
Beringer, A., Hölldobler, S., Kurfeß, F.: Spatial reasoning and connectionist inference. Technical report, Universität Ulm, Abteilung Neuroinformatik (accepted for presentation at IJCAI 93 ), 1992
Denault, M., Karagiannis, D., Kurfeß, F.: Securenet technical report. Technical report, FAW Ulm, 1992
Glesner, M., Huch, M., Pöchmüller, W.: Hardware Implementation for Neural Network. IFIP Workshop on Parallel Architectures on Silicon. Grenoble, 1989
Hölldobler, S., Kurfeß, F.: CHCL - A Connectionist Inference System, in: Fronhoöfer, B., Wrightson, G. (eds.): Parallelization in Inference Systems. Lecture Notes in Computer Science. Springer, 1991
Huch, M., Pochmüller, W., Glesner, M.: Bacchus: a VLSI Architecture for a Large Binary Associative Memory. International Neural Network Conference INNC. Paris, 1990
Kohonen, T.: Associative Memory. Springer Verlag, 1977
Kurfeß F.: Massive Parallelism in Inference Systems, in: Kanal, L., Kumar, V., Modovan, D., Suttner C. ( eds. ): Parallel Processing for Machine Intelligence. Elsevier, 1993
Palm, G.: On Associative Memory. Biol. Cybern. 31, 19–31, 1980
Palm, G.: Assoziatives Gedachtnis und Gehirntheorie, in: Spektrum der Wissenschaft, 1988
Palm, G.: Local Learning Rules and Sparse Coding in Neural Networks, in: Eckmiller, R. ( ed. ): Advanced Neural Computers. 1990
Palm, G., Bonhoeffer, T.: Parallel Processing for Associative and Neuronal Networks, in: Biol. Cybern., 201–204, 1984
Palm, G. and Palm, M.: Parallel associative networks: The PAN System and the BACCHUS-Chip, in: Ramacher, U., Rückert, U. Nossek, J.A. (eds.): Microelectronics for Neural Networks. Kyrill & Method Verlag, Munchen, 411–416, 1991
Palm, G., Rückert, U., Ultsch, A.: Wissensverarbeitung in neuronaler Architektur, in: Brauer, W., Hernandez, D. (eds.): Verteilte Kiinstliche Intelligenz und kooperatives Arbeiten. Informatik-Fachberichte. Springer Verlag, Berlin, Heidelberg, New York, 1991
Palm, G., Stellmann, U., Schwenker, F.: Analyse, Darstellung und ahnlichkeitserhaltende Codierung von Daten. Submitted for publication, 1993
Pietrek, G.: Neuronaler Klassifikatior. WINA Technical Report, Informatik, Universität Dortmund, 1992
Pöchmüller, W., Glesner, M.: A Cascadable VLSI Architecture for the Realization of Large Binary Associative Networks. International Workshop on VLSI for Artificial Intelligence and Neural Networks. Oxford, 1990
Ultsch, A., et al.: Optimizing Logical Proofs with Connectionist Networks. Int. Conf. Artificial Neural Networks. Helsinki, 1991
Ultsch, A. Siemon, H.P.: Kohonen’s self organizing feature map for exploratory data analysis, in: International Neural Network Conference. 305–308, 1990
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Palm, G. (1993). The PAN System and the WINA Project. In: Spies, P.P. (eds) Europäischer Informatik Kongreß Architektur von Rechensystemen Euro-ARCH ’93. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-78565-8_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-78565-8_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57315-9
Online ISBN: 978-3-642-78565-8
eBook Packages: Springer Book Archive