Abstract
In this paper representation in connectionist symbol processing is addressed. There is a putative view that symbol processing requires structural representations and sensitive-to-structure procedures. Here it is proposed that symbolic information processing is based on causal nonstructural representations when computation is massively-parallel. Such representations are formed causally and need not be structural in the sense of constituent symbolic structures. A method of causal representation construction is presented along with a simple example. An implementation of the method in Simple Recurrent Network is shown.
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
Honavar V. Symbolic artificial intelligence and numeric artificial neural networks: towards a resolution of the dichotomy. In Sun R. Bookman LA. (Eds.) Computational architectures integrating neural and symbolic processes. Kluwer Academic Publisher 1995; 351–388
Special issue on connectionist symbol processing. Artificial Intelligence 1990; 46(1–2)
Chrisman L. Learning Recursive Distributed Representations for Holistic Computation. Connection Science 1991; 3 (4): 345–366
Butler K. Towards a Connectionist Cognitive Architecture. Mind & Language 1991; 6 (3): 252–272
Pozarlik R. An unstructured representation for subsymbolic computation. Proc. of the Third World Congress of Neural Networks. Lawrence Erlbaum Associates, Hillsdale NJ 1995; 2: 309–312
Pozarlik R. An unstructural approach to natural language processing in neural networks. Tech. Rep. ICT-48–95, Doctoral dissertation, Institute of Engineering Cybernetics, Wroclaw University of Technology, 1995
Elman JL. Distributed Representations, Simple Recurrent Networks, and Grammatical Structure. Machine Learning 1991; 7: 195–225
Langloh N, Cottam R, Vounckx R, Cornelis J. Towards distributed statistical processing - aquarium: a query and reflection interaction using magic: mathematical algorithms generating interdependent confidences. In Smith S, Neale RF. (Eds.) ESPRIT Basic Research Series, Optical Information Technology. Springer-Verlag, Berlin 1993; 303–319
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag London Limited
About this paper
Cite this paper
Pozarlik, R. (1998). Connectionist Symbol Processing with Causal Representations. In: Bullinaria, J.A., Glasspool, D.W., Houghton, G. (eds) 4th Neural Computation and Psychology Workshop, London, 9–11 April 1997. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-1546-5_25
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1546-5_25
Publisher Name: Springer, London
Print ISBN: 978-3-540-76208-9
Online ISBN: 978-1-4471-1546-5
eBook Packages: Springer Book Archive