Hostname: page-component-74656f9884-8r8nv Total loading time: 0 Render date: 2026-11-10T14:57:53.320Z Has data issue: false hasContentIssue false
  • English
  • Français

Parallel reasoning in structured connectionist networks: Signatures versus temporal synchrony

Review products

Commentary onL.Shastri and V.Ajjanagadde (1993) From simple associations to systematic reasoning: A connectionist representation of rules, variables, and dynamic bindings using temporal synchrony. BBS 16:417–494.

Published online by Cambridge University Press:  04 February 2010

Trent E. Lange  and
Michael G. Dyer
Trent E. Lange
Affiliation:
Artificial Intelligence Laboratory, Computer Science Department, University of California, Los Angeles, CA 90024. lange@cs.ucla.edu; dyer@cs.ucla.edu
Michael G. Dyer
Affiliation:
Artificial Intelligence Laboratory, Computer Science Department, University of California, Los Angeles, CA 90024. lange@cs.ucla.edu; dyer@cs.ucla.edu
Get access Rights & Permissions [Opens in a new window]

Extract

Shastri & Ajjanagadde (1993) (S&A) argue convincingly that both structured connectionist networks and parallel dynamic inferencing are necessary for reflexive reasoning - a kind of inferencing and reasoning that occurs rapidly, spontaneously, and without conscious effort, and which seems necessary for everyday tasks such as natural language understanding. As S&A describe, reflexive reasoning requires a solution to the dynamic binding problem, that is, how to encode systematic and abstract knowledge and instantiate it in specific situations to draw appropriate inferences. Although symbolic artificial intelligence systems trivially solve the dynamic binding problem using computers' registers and pointers, it has remained a difficult problem for connectionist systems (see Fodor & Pylyshyn 1988). S&A's temporal synchrony solution to the dynamic binding problem using synchronous firing of argument units and the entities that are bound to them illustrates one way in which connectionist networks can do thisusing a constrained but important class of long-term knowledge rules. Their structured connectionist solution allows dynamic inferencing to proceed in parallel and therefore has a number of advantages for reflexive reasoning over most other connectionist and symbolic systems.

Information

Type
Continuing Commentary
Information
Behavioral and Brain Sciences , Volume 19 , Issue 2 , June 1996 , pp. 328 - 331
Copyright
Copyright © Cambridge University Press 1996

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Ajjanagadde, V. G. (1991) Abductive reasoning in connectionist networks: Incorporating variables, background knowledge, and structured explananda. Technical report WSI-91–7. Wilhelm-Schickard-Institute, University of Tuebingen, Germany. [rLS]Google Scholar
Barnden, J. (1991) The power of some unusual connectionist data-structuring techniques. In: Advances in connectionist and neural computation theory. Ablex. [TEL]Google Scholar
Bechtel, W. & Abrahansen, A. (1991) Connectionism and the mind. Blackwell. [LB]Google Scholar
Braine, M. D. & O'Brien, D. P. (1991) A theory of if: Lexical entry, reasoning program, and pragmatic principles. Psychological Review 98:182–203. [LB]Google Scholar
Braine, M. D., Reiser, B. J. & Rumain, B. (1984) Some empirical justifications for a theory of natural propositional logic. The Psychology of teaming and Motivation 18:313–71. [LB]Google Scholar
Cottrell, G. W. (1993) From symbols to neurons: Are we there yet? Behavioral and Brain Sciences 16:454. [TEL]CrossRefGoogle Scholar
Daneman, M. & Carpenter, P. A. (1980) Individual differences in working memory and reading. Journal of Verbal Learning and Verbal Beliavior 19:450–66. [TEL]Google Scholar
Dawson, M. R. W. & Berkeley, I. (1993) Making a middling mousetrap. Behavioral and Brain Sciences 16:454–55. [LB]CrossRefGoogle Scholar
Fahlman, S. E. (1979) NETL: A system for representing and using real world knowledge. MIT Press. [TEL]Google Scholar
Feldman, J. A. & Ballard, D. H. (1982) Connectionist models and their properties. Cognitive Science 6(3):205–54.[TEL]Google Scholar
Fodor, J. A. (1975) The language of thought. Crowell. [LB]Google Scholar
Fodor, J. A. (1987) Psychosemantics. MIT Press. [LB]CrossRefGoogle Scholar
Fodor, J. D., Fodor, J. A. & Garrett, M. F. (1975) The psychological unreality of semantic representations. Linguistic Inquiry 4:515–31. [LB]Google Scholar
Fodor, J. A. & Pylyshyn, Z. W. (1988) Connectionism and cognitive architecture: A critical analysis. In: Connections and symbols, ed. Pinker, S. & Mehler, J.. MIT Press. [TEL]Google Scholar
Henderson, J. (1988) Connectionist syntactic parsing using temporal variable binding. Journal of Psycholinguistic Research 23:353–79. [TEL, rLS]Google Scholar
Hendler, J. (1988) Integrating marker-passing and problem solving: A spreading activation approach to improved choice in planning. Erlbaum. [TEL]Google Scholar
Hinton, G. E. (1981) Implementing semantic networks in parallel hardware. In: Parallel models of associative memory, ed. Hinton, G E. & Anderson, J. A.. Erlbaum. [TEL]Google Scholar
Hölldobler, S. (1990) CHCL: A connectionist inference system for Horn Logic based on the connection method and using limited resources. Technical Report 90-042, International Computer Science Institute, Berkeley, CA [TEL]Google Scholar
Johnson-Laird, P. N., Byrne, R. M., Schaeken, W. (1992) Prepositional reasoning by model. Psychological Review 99:418–39. [LB]CrossRefGoogle Scholar
Just, M. A. & Carpenter, P. A. (1992) A capacity theory of comprehension: Individual differences in working memory. Psychological Review 99(l):122–49. [TEL, rLS]Google Scholar
King, J. & Just, M. A. (1991) Individual differences in syntactic processing: The role of working memory. Journal of Memory and Language 30:580–602. [TEL]Google Scholar
Kitano, H. (1991) DmDialog: A speech-to-speech dialog translation system. Machine Translation 5:301–38. [TEL]Google Scholar
Lange, T. (1992) Lexical and pragmatic disambiguation and reinterpretation in connectionist networks. International Journal of Man-Machine Studies 36:191–220. [TEL]Google Scholar
Lange, T. (1995) A structured connectionist approach to inferencing and retrieval in: Computational architectures integrating neural and symbolic processes, ed. Sun, H. & Bookman, L.. Kluwer. [TEL]Google Scholar
Lange, T. & Dyer, M. (1989) High-level inferencing in a connectionist network. Connection Science 1:181–217. [TEL]Google Scholar
Lange, T. & Wharton, C. M. (1993) Dynamic memories: Analysis of an integrated comprehension and episodic retrieval model. Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence. Morgan Knufmann. [TEL]Google Scholar
MacDonald, M. C, Just, M. A. & Carpenter, P. A.Working memory constraints on the processing of syntactic ambiguity. Cognitive Psychology 24:56–98. [TEL]Google Scholar
Miikkulainen, R. & Dyer, M. G. (1991) Natural language processing with modular PDP networks and distributed lexicon. Cognitive Science 15:343–399. [TEL]Google Scholar
Miller, G. A. (1956) The magical number seven, plus or minus two: Some limits on our capacity for processing information. Psychological Review 63(2):81–97. [TEL]Google Scholar
Oaksford, M. & Malloch, M. (1993) Computational and biological constraints in the psychology of reasoning. Behavioral and Brain Sciences 16:468–69. [LB]CrossRefGoogle Scholar
Riesbeck, C. K. & Martin, C. E. (1986) Direct memory access parsing. In: Experience, memory, and reasoning, ed. Kolodner, J. & Riesbeck, C.. Erlbaum. [TEL]Google Scholar
Rumelhart, D. E. (1980) Schemata: The building blocks of cognition. In: Theoretical issues in reason and comprehension, ed. Spiro, R., Bruce, B. & Brewer, B.. Erlbaum.Google Scholar
Rumelhart, D. E. & McClelland, J. L. (1986) Parallel distributed processing: Explorations in the microstructure of cognition, vol. 1. Bradford/MIT press. [TEL]Google Scholar
St. John, M. (1992) The story gestalt: A model of knowledge-intensive processes in text comprehension. Cognitive Science 16:271–306. [TEL]Google Scholar
Shastri, L. (in preparation) Learning context-sensitive rules in a connectionist system based on temporal synchrony. [TEL]Google Scholar
Shastri, L. & Ajjanagadde, V. (1993) From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic binds using temporal synchrony. Behavioral and Brain Sciences 16:417–94. [LB, TEL, rLS]Google Scholar
Shastri, L. & Grannes, D. J. (1996) A connectionist treatment of negation and inconsistency. Proceedings of the Eighteenth Conference of the Cognitive Science Society. Erlbaum [rLS]Google Scholar
Smolensky, P. (1988) On the proper treatment of connectionism. Behavioral and Brain Sciences 11:1–74. [TEL]CrossRefGoogle Scholar
Smolensky, P. (1990) Tensor product variable binding and the representation of symbolic structure in connectionist systems. Artificial Intelligence 46(1–2):159–216. [TEL]Google Scholar
Sumida, R. A. & Dyer, M. G. (1989) Storing and generalizing multiple instances while maintaining knowledge-level parallelism. Proceedings of 1JCAI-89. Morgan Kaufmann. [TEL]Google Scholar
Sun, R. (1995) Robust reasoning: Integrating rule-based and similarity-based reasoning. Artificial Intelligence 75(2):241–296. [TEL]Google Scholar
Touretzky, D. (1990) Connectionism and compositional semantics. In: Advances in connectionist and neural computation theory. Ablex. [TEL]Google Scholar
Touretzky, D. S. & Hinton, G. E. 91988) A distributed connectionist production system. Cognitive Science 12(3):423–66. [TEL]CrossRefGoogle Scholar
Ullman, J. D. & van Gelder, A. (1988) Parallel complexity of logical query programs. Algorithmica 3:5–42. [TEL]CrossRefGoogle Scholar
Velmans, M. 91991) Is human information processing conscious? Behavioral and Brain Sciences 14(4):651–726. [TEL]Google Scholar