System for continuous logic computation and method of using same

Data processing: artificial intelligence – Knowledge processing system – Knowledge representation and reasoning technique

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

706 31, G06F 1518

Patent

active

057992967

ABSTRACT:
A continuous logic system using a neural network is characterized by defining input and output variables that do not use a membership function, by employing production rules (IF/THEN rules) that relate the output variables to the input variables, and by using the neural network to compute or interpolate the outputs. The neural network first learns the given production rules and then produces the outputs in real time. The neural network is constructed of artificial neurons each having only one significant processing element in the form of a multiplier. The neural network utilizes a training algorithm which does not require repetitive training and which yields a global minimum to each given set of input vectors.

REFERENCES:
patent: 4979126 (1990-12-01), Pao et al.
patent: 5058034 (1991-10-01), Murphy et al.
patent: 5073867 (1991-12-01), Murphy et al.
patent: 5077677 (1991-12-01), Murphy et al.
patent: 5103405 (1992-04-01), Murphy et al.
patent: 5295061 (1994-03-01), Katayama et al.
patent: 5371809 (1994-12-01), Desieno
patent: 5408588 (1995-04-01), Ulug
patent: 5467428 (1995-11-01), Ulug
Basic Issues on Fuzzy Rules and their Application to Fuzzy Control by Didier Dubois and Henri Prade, IJCAI '91 Workshops. Sydney, Australia, Aug. 1991 Proceedings.
Polynomial Functions Can Be Realized by Finite Size Multilayer Feedforward Neural Networks by Naohiro Toda, Ken-ichi Funahashi and Shiro Usui, 1991 IEEEE International Joint Conference on Neural Networks, vol. 1 of 3, Nov. 1991.
A Connnectionist Production System with Approximate Matching Function by Katsuaki Sanou, Steve G. Romaniuk, and Lawrence O. Hall, Second IEEE International Conference on Fuzzy Systems, San Francisco, CA, Mar. 28-Apr. 1, 1993, vol. 1.
Neural-Network-Based Fuzzy Logic Control and Decision System by Lin et al., IEEE Trans. on Computers, vol. 40, No. 12, Dec. 1991.
Classification of Blood volumes. Pulse Signals Using an Artificial Neural Network Bayesian Classifier by Heimer et al., 12th Southern Biomed Engineering Conf., Apr. 2-4, 1993, pp. 87-89.
Synthetic Neural Systems in VLSI by Akers et al., 1990, pp. 317-336.
T. Krile, et al., "Polynomial Neural Networks for Airborne Applications," 1989 Conf. on National Aerospace and Electronics, pp. 682-687, May 1989.
B. Malakooti and Y.Q. Zhou, "An Artificial Neural Network for Approximating Polynomial Functions," Int'l. Joint Conf. on Neural Networks, pp. III-966 to III-971. Jun. 1992.
M.-S. Chen and M.T. Manry, "Conventional Modeling of the Multilayer Perceptron Using Polynomial Basis Functions," IEEE TRans. on Neural Networks, vol. 4(1), pp. 164-166, Jan. 1993.
C.-H. Chang, et al., "Polynomial and Standard Higher Order Neural Network," 1993 Int'l. Conf. on Neural Networks, pp. 989-994, Mar. 1993.

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

System for continuous logic computation and method of using same does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with System for continuous logic computation and method of using same, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System for continuous logic computation and method of using same will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-46727

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