Abstract
A novel purely connectionist implementation of proposi- tional logic is constructed by combining Correlation Matrix Memory operations, tensor products and simple control circuits. The implementa- tion is highly modular and expandable and in its present form it not only allows forward rule chaining but also implements is a hierarchy traversal which results in interesting behavior even in its simplest form.
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.
Similar content being viewed by others
References
C Orovas J Austin. Cellular associative symbolic processing for pattern recognition. MFCS’ 98 workshop on Grammer Learning, pages 269–280, 1998.
J Austin. Correlation matrix memories for knowledge manipulation. In International Conference on Neural Networks, Fuzzy Logic, and Soft Computing: Iizuka, Japan, 1994.
J Austin. Distributed associative memories for high speed symbolic reasoning. International Journal on Fuzzy Sets and Systems, 82(2):223–233, 1995. Invited paper to the special issue on Connectionist and Hybrid Connectionist Systems for Approximate Reasoning.
CP Dolan and P Smolensky. Tensor product production system: a modular architecture and representation. Connection Science, (1):53–68, 1989.
JV Kennedy, J Austin, R Pack, and B Cass. C-NNAP: A parallel processing architecture for binary neural networks. In International Conference on Neural Networks (ICANN 95), Perth, Australia, November 1995.
D Kustrin, J Austin, and A Sanders.Application of correlation memory matrices in high frequency asset allocation. In M Niranjan, editor, Fifth International Conference on Artificial Neural Networks. IEE, 1997.
D McDermott. Artificial intelligence meets natural stupidity. SIGART Newsletter, (57), 1976.
S O’Keefe. Neural-Based Content Analysis of Document Images. PhD thesis, Department of Computer Science, University of York, 1997.
M Turner and J Austin. Matching performance of binary correlation matrix memories. Neural Networks, 10(9):1637–1648, 1997.
M Turner and J Austin. A neural network technique for chemical graph matching. In M Niranjan, editor, Proceedings of the Fifth International Conference on Artificial Neural Networks. IEE, 1997.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kustrin, D., Austin, J. (2001). Connectionist Propositional Logic A Simple Correlation Matrix Memory Based Reasoning System. In: Wermter, S., Austin, J., Willshaw, D. (eds) Emergent Neural Computational Architectures Based on Neuroscience. Lecture Notes in Computer Science(), vol 2036. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44597-8_38
Download citation
DOI: https://doi.org/10.1007/3-540-44597-8_38
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42363-8
Online ISBN: 978-3-540-44597-5
eBook Packages: Springer Book Archive