This Article 
 Bibliographic References 
 Add to: 
A Browser for Large Knowledge Bases Based on a Hybrid Distributed/Local Connectionist Architecture
March 1991 (vol. 3 no. 1)
pp. 89-99

A browser concept based on a connectionist architecture is presented. The concept utilizes both distributed and local representations. A proof-of-concept system is implemented for an integrally developed, Honeywell-proprietary knowledge acquisition tool. In the browser, concepts and relations in a knowledge base are represented using microfeatures. The microfeatures can encode semantic attributes, structural features, contextual information, etc. Desired portions of the knowledge base can then be associatively retrieved based on a structured cue. An ordered list of partial matches is presented to the user for selection. Microfeatures can also be used as bookmarks-they can be placed dynamically at appropriate points in the knowledge base and subsequently used as retrieval cues. The browser concept can be applied wherever there is a need for conveniently inspecting and manipulating structured information.

[1] D. H. Ackley, G. E. Hinton, and T. J. Sejnowski, "A learning algorithm for Boltzmann machines,"Cognitive Sci., vol. 9, pp. 147-169, 1985.
[2] E. B. Baum, J. Moody, and F. Wilczek, "Internal representations for associative memory," manuscript, Institute for Theoretical Physics, Univ. of California, Santa Barbara, CA 93106, 1987.
[3] E. L. Cochran, "KLAMShell: A domain-specific knowledge acquisition shell," Tech. Rep. CSDD-88-I6301-1, Honeywell CSDD, 1000 Boone Avenue North, Golden Valley, MN 55427, 1988.
[4] J. A. Fodor and Z. W. Pylyshyn, "Connectionism and cognitive architecture: A critical analysis,"Cognition, vol. 28, nos. 1-2, 1988.
[5] S. I. Gallant, "Connectionist expert systems,"Commun. ACM, vol. 31, no. 2, pp. 152-169, Feb. 1988.
[6] D. E. Goldberg,Genetic Algorithms in Search, Optimization, and Machine Learning. Reading, MA: Addison-Wesley, 1989.
[7] M. Gordon, "Probabilistic and genetic algorithms for document retrieval,"Commun. ACM, vol. 31, no. 10, pp. 1208-1218, 1988.
[8] S. Grossberg, Review of "Perceptrons,"AI Magazine, vol. 10, no. 2, 1989.
[9] W. D. Hillis,The Connection Machine. Cambridge, MA: MIT Press, 1985.
[10] Parallel Models of Associative Memory, E. Hinton and J.A. Anderson, eds., Lawrence Erlbaum Associates, Hillsdale, N.J., 1989 (updated edition).
[11] G. E. Hinton, J. L. McClelland, and D. E. Rumelhart, "Distributed representations," inParallel Distributed Processing, Vol. 1. Cambridge, MA: M.I.T. Press, 1986, pp. 77-109.
[12] W. P. Jones, "On the applied use of human memory models: The memory extender personal filing system," Tech. Rep. HI-059-86, Microelectronics and Computer Technology Corp., 9430 Research Boulevard, Echelon #1, Austin, TX 78759, Mar. 1986.
[13] Y. Le Cun, "Learning process in an asymmetric threshold network,"Disordered Systems and Biological Organization, E. Bienenstock, Ed. New York: Springer Verlag, 1986.
[14] R. P. Lippman, "An introduction to computing with neural nets,"IEEE ASSP Msg., vol. 4, pp. 4-22, 1987.
[15] J.L. McClelland and D.E. Rumelhart, Eds.,Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Vol 2: Applications, MIT Press/Bradford Books, 1986.
[16] D.B. Parker, "Learning logic," TR-47, Center for Computational Research in Economics and Management Science, MIT, 1985.
[17] S. Pinker and A. Prince, "On language and connectionism: Analysis of a parallel distributed model of language acquisition,"Cognition, vol. 28, nos. 1-2, 1988.
[18] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, "Learning internal representations by error propagation," ICS Rep. 8506, Institute for Cognitive Science, Univ. of California, San Diego, Sept. 1985.
[19] D.E. Rumelhart and D. McClelland, eds.,Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vols. 1-2, MIT Press, Cambridge, Mass., 1986.
[20] G. Salton, "Another look at automatic text-retrieval systems,"Commun. ACM, vol. 29, no. 7, pp. 648-656, 1986.
[21] G. Salton and C. Buckley, "Parallel text search methods,"Commun. ACM, vol. 31, no. 2, pp. 202-215, 1988.
[22] G. Salton and M. J. McGill,Introduction to Modern Information Retrieval(Computer Series). New York: McGraw-Hill, 1983.
[23] T. Samad, "Towards connectionist rule-based systems," inProc. IEEE Int. Conf. Neural Networks, 1988.
[24] T. Samad, "Hybrid distributed/local connectionist architectures," in preparation.
[25] C. Stanfill and B. Kahle, "Parallel free-text search on the connection machine system,"Commun. ACM, vol. 29, pp. 1229-1239, Dec. 1986.
[26] C. Stanfil and D. Waltz, "Toward memory-based reasoning,"Commun. ACM, vol. 29, pp. 1213-1228, 1986.
[27] H. Stone, "Parallel querying of large databases: A case study,"IEEE Comput. Mag., pp. 11-21, Oct. 1987.
[28] D.S. Touretzky and G.E. Hinton, "A distributed connectionist production system," Tech. Rep. CMU-CS-86-172, Comput. Sci. Dep., Carnegie Mellon Univ., Pittsburgh, PA, 1986.
[29] J. Voevodsky, "Plato/Aristotle: A neural net knowledge processor," inProc. IEEE First Annu. Int. Conf. Neural Networks, 1987.
[30] P. Werbos, "Beyond regression: New tools for prediction and analysis in the behavioral sciences," Ph.D. dissertation, Harvard Univ. Committee on Applied Mathematics, 1974.

Index Terms:
browser; large knowledge bases; hybrid distributed/local connectionist architecture; proof-of-concept system; knowledge acquisition tool; microfeatures; semantic attributes; structural features; contextual information; knowledge acquisition; knowledge based systems
T. Samad, P. Israel, "A Browser for Large Knowledge Bases Based on a Hybrid Distributed/Local Connectionist Architecture," IEEE Transactions on Knowledge and Data Engineering, vol. 3, no. 1, pp. 89-99, March 1991, doi:10.1109/69.75892
Usage of this product signifies your acceptance of the Terms of Use.