Method for use in a processing system having a network that gene

Details Method for use in a processing system having a network that gene Method for use in a processing system having a network that gene

1993-06-14

1997-12-09

Downs, Robert W.

G06F 1518

Patent

active

056968817

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: 5153439 (1992-10-01), Gozoni et al.
patent: 5168549 (1992-12-01), Takagi et al.
patent: 5255344 (1993-10-01), Takagi et al.
patent: 5295061 (1994-03-01), Katayama et al.
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, UCAI '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 IEEE International Joint Conference on Neural Networks, vol. 1 of 3, Nov. 1991.
A Connectionist 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.
Lin et al, "Neural Network-Based Fuzzy Logic Control and Decision System", IEEE Transactions on Computers, vol. 40, No. 12, Dec. 1991.
Heimer et al, "Classification of Blood Volume Pulse Signals Using an Artificial Neural Network Bayesian Classifier", 12th Southern Biomed Eng Conference, Apr. 2-4 1993, pp. 87-89.
Akers et al, "Synthetic Neural Systems in VLSI", 1990 pp. 318-336.
Hayashi et al, "Neural Network Driven Fuzzy Reasoning Model", Proc 28th SICE Annual Conference Jul. 1989 pp. 1343-1346.
Graf et al, "A Reconfigurable CMOS Neural Network", 1990, 1990 IEEE Int'l Solid State Circuits Conference, pp. 144-145.
Baocheng et al, "A New Approach of Fuzzy Control by Using Neural Network", Proc. of the Intelligent Vehicles '92 Symposium, Jun. 29-Jul. 1, 1992, pp. 321-324.
Keller et al, "Fuzzy Logic Inference Neural Networks", SPIE vol. 1192 Intelligent Robots & Comp Vision VIII: Algorithms & Techniques, Dec. 1989, pp. 582-591.

Affiliated with

Also associated with

Rating

Method for use in a processing system having a network that gene 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 for use in a processing system having a network that gene, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for use in a processing system having a network that gene will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1614797