Method and apparatus for refinement of learning in expert networ

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

G06F 1518

Patent

active

056490666

ABSTRACT:
A method for constructing an expert network apparatus from a specific rule-based expert system, having a certainty factor, through the use of a first-order network structure comprising regular node structures and weighted connections and a second-order network comprising regular nodes, operation nodes and connections. Also disclosed are related methods for implementing backpropagation learning on an acyclic, event-driven, expert network apparatus and for improving the rule-base of a rule-based expert system. Further disclosed is an event-driven expert network of high-level nodes and methods for implementing backpropagation learning thereon.

REFERENCES:
patent: 4326259 (1982-04-01), Cooper et al.
patent: 4593367 (1986-06-01), Slack et al.
patent: 4912647 (1990-03-01), Wood
patent: 4912649 (1990-03-01), Wood
patent: 4912651 (1990-03-01), Wood et al.
patent: 4912652 (1990-03-01), Wood
patent: 4912653 (1990-03-01), Wood
patent: 4912654 (1990-03-01), Wood
patent: 4912655 (1990-03-01), Wood
patent: 4914603 (1990-04-01), Wood
patent: 4918620 (1990-04-01), Ulug
patent: 4979126 (1990-12-01), Pao et al.
patent: 5121467 (1992-06-01), Skeirik
patent: 5130936 (1992-07-01), Sheppard et al.
patent: 5168549 (1992-12-01), Takagi et al.
patent: 5201026 (1993-04-01), Tsuiki
LiMin Fu, "Rule Learning by Searching on Adapted NETS," AAAI-91 Conference, 1991.
K, Hirota, W. Pedrycz, "Fuzzy Logic Neural Networks: Design and Computations," International Joint Conference on Neural Networks, 1991.
Hirota et al., Fuzzy Logic Neural Networks: Design and Computations, in 1991 IEEE International Joint Conference on Neural Networks, vol. 1, Nov. 1991, pp. 152-157.
Fu, Rule Learning by Searching on Adapted Nets, in Proceedings of American Association of Artificial Intelligence Conference, Jul. 1991, pp. 590-595.
Lacher et al., Expert Networks: A Neural Network Connection to Symbolic Reasoning Systems, in Proceedings of the 4th Florida Artificial Intelligence Research Symposium, Apr. 1991, pp. 12-16.
Krieger et al., Neuronet--A Distributed Real-Time System for Monitoring Neurophysiologic Function in the Medical Environment, in IEEE Computer, Mar. 1991, pp. 45-55.
Hruska et al., Learning in Acyclic Expert Networks, in Second Proceedings of the Second Workshop on Neural Networks: Academic/Industrial/NASA Defense, Feb. 1991, pp. 181-184.
Lacher et al., Backpropagation Learning in Expert Networks, FSUCS Technical Report 91-015, Jan. 1991.
Lacher et al., Expert Networks: A Neural Network Connection to Symbolic Reasoning Systems, FSUCS Technical Report 90-092, Sep. 1990.
Kuncicky et al., Hybrid Systems: The Equivalence of Rule-Based Expert System and Artificial Intelligence Neural Network Inference, FSUCS Technical Report 90-091, 1990.
Hruska et al., Learning in Acyclic Neural Networks, FSUCS Technical Report 90-052, May 1990.
Kuncicky, The Transmission of Knowledge Between Neural Networks and Expert Systems, in Proceedings of the [First] Workshop on Neural Networks: Academic/Industrial/NASA/Defenst, Feb. 5-6, 1990, pp. 311-319.
Fu, Integration of Neural Heuristics into Knowledge-Based Inference, in Connection Science, 1990.
Fu, "Refinement of Medical Knowledge Bases: A Neural Network Approach", Proc of 3rd Annual IEEE Symposium on Computer Based Medical Systems, Jun. 3-6 1990, pp. 290-297.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Method and apparatus for refinement of learning in expert networ does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method and apparatus for refinement of learning in expert networ, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for refinement of learning in expert networ will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-1498078

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.