Data processing: artificial intelligence – Neural network – Structure
Reexamination Certificate
2006-11-21
2006-11-21
Davis, George (Department: 2129)
Data processing: artificial intelligence
Neural network
Structure
C706S013000
Reexamination Certificate
active
07139740
ABSTRACT:
In a method and system for developing a neural system adapted to perform a specified task, a population of neural systems is selected, each neural system comprising an array of interconnected neurons, and each neural system is encoded into a representative genome. For a given genome, a processing gene encodes a neural output function for each neuron, and the connections from each neuron are encoded by one or more connection genes, each connection gene including a weight function. The given neural system is operated to perform the specified task during a trial period, and performance is continually monitored during the trial period. Reinforcement signals determined from the continually monitored performance are applied as inputs to the functions respectively associated with each of the processing genes and connection genes of the given neural system. At the conclusion of the trial period, the fitness of the given neural system for performing the specified task is determined, usefully as a function of the reinforcement signals applied during the trial period. A set of genomes, respectively representing the neural systems of the population that have been determined to have the highest fitness values, are selected for use in forming a new generation of neural systems.
REFERENCES:
patent: 4979126 (1990-12-01), Pao et al.
patent: 4994982 (1991-02-01), Duranton et al.
patent: 5093899 (1992-03-01), Hiraiwa
patent: 5136686 (1992-08-01), Koza
patent: 5140530 (1992-08-01), Guha et al.
patent: 5214746 (1993-05-01), Fogel et al.
patent: 5245696 (1993-09-01), Stork et al.
patent: 5249259 (1993-09-01), Harvey
patent: 5283855 (1994-02-01), Motomura et al.
patent: 5349646 (1994-09-01), Furuta et al.
patent: 5375250 (1994-12-01), Van den Heuvel
patent: 5398302 (1995-03-01), Thrift
patent: 5400436 (1995-03-01), Nara et al.
patent: 5402522 (1995-03-01), Alkon et al.
patent: 5428710 (1995-06-01), Toomarian et al.
patent: 5452402 (1995-09-01), Sakiyama et al.
patent: 5455891 (1995-10-01), Hirotsu et al.
patent: 5459817 (1995-10-01), Shima
patent: 5515477 (1996-05-01), Sutherland
patent: 5566273 (1996-10-01), Huang et al.
patent: 5568590 (1996-10-01), Tolson
patent: 5617483 (1997-04-01), Osawa
patent: 5633988 (1997-05-01), Takatori et al.
patent: 5640494 (1997-06-01), Jabri et al.
patent: 5704016 (1997-12-01), Shigematsu et al.
patent: 5717832 (1998-02-01), Steimle et al.
patent: 5720002 (1998-02-01), Wang
patent: 5729662 (1998-03-01), Rozmus
patent: 5761381 (1998-06-01), Arci et al.
patent: 5812992 (1998-09-01), de Vries
patent: 5832466 (1998-11-01), Feldgajer
patent: 5835901 (1998-11-01), Duvoisin, III et al.
patent: 5841949 (1998-11-01), Nakaya et al.
patent: 5864832 (1999-01-01), Meyers
patent: 5870728 (1999-02-01), Yatsuzuka et al.
patent: 5870729 (1999-02-01), Yoda
patent: 5920851 (1999-07-01), Muller
patent: 5930781 (1999-07-01), Toomarian et al.
patent: 5937432 (1999-08-01), Yamaguchi et al.
patent: 5974404 (1999-10-01), Moed et al.
patent: 6038338 (2000-03-01), Nguyen
patent: 6151592 (2000-11-01), Inazumi
patent: 6205556 (2001-03-01), Watanabe et al.
patent: 6269351 (2001-07-01), Black
patent: 6349293 (2002-02-01), Yamaguchi
patent: 6366897 (2002-04-01), Means et al.
patent: 6415272 (2002-07-01), Ulyanov
patent: 6449603 (2002-09-01), Hunter
patent: 6516309 (2003-02-01), Eberhart et al.
patent: 6553357 (2003-04-01), Mathias et al.
patent: 6601053 (2003-07-01), Schaffer et al.
patent: 2002/0059154 (2002-05-01), Rodvold
patent: 2003/0004904 (2003-01-01), Kirshenbaum
patent: 2003/0014378 (2003-01-01), Goodnight et al.
patent: 2003/0018598 (2003-01-01), Cawse et al.
Kobayashi et al, “A New Indirect Encoding Method with Variable Length Gene Code to Optimize Neural Network Structures”, IEEE, IJCNN, Jul. 1999.
Hallinan, J., et al., 1998;Cooperative Evolution Of A Neural Classifier And Feature Subset,; Proc. 2nd Asia-Pacific Conference on Simulated Evolution and Learning.
Harter, D. et al., 2001;Models of Ontogenetic Development for Autonomous Adaptive Systems; Proceedings of the 23rd Annual Conference of the Cognitive Science Society, pp. 405-410.
Hochman, R., et al., 1996;Using The Genetic Algorithm To Build Optimal Neural Networks For Fault-Prone Module Detection; In Proc. the Seventh Int. Symposium on Software Reliablity Engineering, pp. 152-162; White Plains, N.Y.
Keane, M.A., et al., 2002;Automatic Synthesis Using Genetic Programming of an Improved General-Purpose Controller for Industrially Representative Plants; Evolvable Hardware, 2002; pp. 113-122.
Michel, O., 1995;An Artificial Life Approach for the Synthesis of Autonomous Agents; In J. Alliot, E. Lutton, E. Ronald, M. Schoenauer, and D. Snyers (Eds.), Proceedings of the European Conference on Artificial Evolution. Springer-Verlag.
Kaelbling, L.P., et al.Reinforcement Learning: A Survey, (1996),Journal of Artificial Intelligence Research4: 237-285.
Touretzky, D.S., et al., (1997)Operant Conditioning in Skinnerbots. Adaptive Behavior5:219-247.
Byount-Tak Zhang,et al.,Evolutionary Induction of Sparse Neural Trees, Evolutionary Computation, 1997, vol. 5, No. 2, pp. 213-236.
Byoung-Tak Zhang, et al.,Evolutionary Neural Trees for Modeling and Predicting Complex Systems; Engng. Applic. Artif. Intell.vol. 10, No. 5 pp. 473-483, 1997.
Koza, John R., 1989,Hierarchical Genetic Algorithms Operating on Populations of Computer Programs, Reprinted: Computer Science Department, Stanford University, Stanford, CA; pp. 578-584.
F. Pasemann;Pole-Balancing with Different Evolved Neurocontrollers; Max-Planck-Institute for Mathematics in the Sciences, D-04103 Leipzig, Germany; pp. 1-7.
J.R.Koza, et al.;Evolving Inventions; Scientific American; 2003; pp. 52-59.
H.Lipson, et al.;Automatic Design and Manufacture of Robotic Lifeforms; Nature, vol. 406, Aug. 31, 2000; pp. 974-978.
C.O. Willke, et al.;Evolution of Digital Organisms at High Mutation Rates Leads to Survival of the Flattest; Nature, vol. 412, Jul. 19, 2001; pp. 331-333.
R.E.Lenski, et al.;The Evolutionary Origin of Complex Features; Nature, vol. 423, May 8, 2003; pp. 139-144.
Y. Sahigematsu, et al.;A dynamic Neural Cell Model Driven by Pulse Train; Electrotechnical Laboratory; Umezono Tsukuba Ibaraki JAPAN; pp. 130-133.
P.D. Wasserman, et al.;Neural Networks, What are they and Why is Everybody so Interested in Them Now?; Part 2; Institute of Electrical and Electronics EngineeringExpert, Spring 1988; pp. 10-15.
R.S.Scalero, et al.;A Fast New Algorighm for Training Feedforward Neural Networks; Institute of Electrical and Electronics Engineering; Transactions on Signal Processing. vol. 40, No. 1, Jan. 1992; pp. 202-210.
K.E. Kinnear, Jr.;Evolutionary Computers 1, Basic Algorithms and Operators, Beck, T. et al. (eds) 2000; Institute of Physics Publishing, Bristol; pp. 102-113.
P.J. Angeline;Evolutionary Computers 1, Basic Algorithms and Operators, Beck, T. et al. (eds) 2000; Institute of Physics Publishing, Bristol; pp. 102-113.
D.Tveter;The Pattern Recognition Basis of Artificial Intelligence.
S.L.Blyumin, et al.;Reduction of Adjusting Weights Space Dimension in Feedforward Artificial Neural NetworksTraining; IEEE International Conference on Artificial Intelligence Systems; Sep. 5-10, 2002; p. 242.
S.S.Han, et al.; Optimization of Neural Network Structure and Learning Perameters Using Genetic Algorithms; 8thInternational Conference on Tools with Artifical Intelligence; Nov. 16-19, 1996; Toulousse, France; p. 200.
T.Zhuang, et al.;A Neuron-Weighted Learning Algorithm and its Hardwae Implementation in Associative Memories; IEEE Transactions on Computers, 1993; pp. 636-640.
N.P. Archer, et al.;Learning Bias in Neural Networks and an Approach to Controlling its Effect in Monotonic Classification; IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993; pp. 962-966.
A.K. Bansal;Establishing a Framework for Comparative Analysis of Genome Sequences; IEEE First International Symposium on Intelligence in Neural and Biological Systems May 29-31 1995; p. 84.
M.Hilario, et al.;A Metalevel Architecture for Knowledge-Based neural Network Design; IEEE 9thInternational Conference on Tools with
Davis George
Gardere Wynne & Sewell LLP
LandOfFree
System and method for developing artificial intelligence 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 and method for developing artificial intelligence, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for developing artificial intelligence will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3628823