Data processing: artificial intelligence – Neural network – Learning method
Reexamination Certificate
2007-12-06
2010-10-12
Holmes, Michael (Department: 2129)
Data processing: artificial intelligence
Neural network
Learning method
Reexamination Certificate
active
07814038
ABSTRACT:
In an artificial neural network a method and neuron device that produce weight-adjustment factors, also called error values (116), for pre-synaptic neurons (302a . . .302c) that are used to adjust the values of connection weights (106 . . . 106n) in neurons (100) used in artificial neural networks (ANNs). The amount of influence a pre-synaptic neuron has had over a post-synaptic neuron is calculated during signal propagation in the post-synaptic neuron (422a . . .422n) and accumulated for the pre-synaptic neuron (426) for each post-synaptic neuron to which the pre-synaptic neuron's output is connected (428). Influence values calculated for use by pre-synaptic neurons may further be modified by the post-synaptic neuron's output value (102) (option424), and its error value (116) (option1110).
REFERENCES:
patent: 5050095 (1991-09-01), Samad
patent: 5136687 (1992-08-01), Edelman et al.
patent: 5168550 (1992-12-01), Sakaue et al.
patent: 5212767 (1993-05-01), Higashino et al.
patent: 5257342 (1993-10-01), Takatori et al.
patent: 5293454 (1994-03-01), Kamiya
patent: 5355434 (1994-10-01), Yoneda et al.
patent: 5430829 (1995-07-01), Takatori et al.
patent: 5430830 (1995-07-01), Frank et al.
patent: 5448681 (1995-09-01), Khan
patent: 5450528 (1995-09-01), Chung et al.
patent: 5459817 (1995-10-01), Shima
patent: 5473730 (1995-12-01), Simard
patent: 5555345 (1996-09-01), Komori et al.
patent: 5563983 (1996-10-01), Nozaki et al.
patent: 5572628 (1996-11-01), Denker et al.
patent: 5608843 (1997-03-01), Baird, III
patent: 5613042 (1997-03-01), Chung et al.
patent: 5630020 (1997-05-01), Makram-Ebeid
patent: 5644681 (1997-07-01), Takahashi et al.
patent: 5704016 (1997-12-01), Shigematsu et al.
patent: 5720002 (1998-02-01), Wang
patent: 5748848 (1998-05-01), Tresp
patent: 5768476 (1998-06-01), Sugaya et al.
patent: 5802507 (1998-09-01), Gentric et al.
patent: 5806053 (1998-09-01), Tresp et al.
patent: 5822742 (1998-10-01), Alkon et al.
patent: 5832465 (1998-11-01), Tom
patent: 5832466 (1998-11-01), Feldgajer
patent: 5845051 (1998-12-01), Oh
patent: 5870728 (1999-02-01), Yatsuzuka et al.
patent: 5930781 (1999-07-01), Toomarian et al.
patent: 5946675 (1999-08-01), Sutton
patent: 6009418 (1999-12-01), Cooper
patent: 6192353 (2001-02-01), Assaleh et al.
patent: 6247001 (2001-06-01), Tresp et al.
patent: 6249781 (2001-06-01), Sutton
patent: 6263325 (2001-07-01), Yoshida et al.
patent: 6269351 (2001-07-01), Black
patent: 6272479 (2001-08-01), Farry et al.
patent: 6347309 (2002-02-01), De Tremiolles et al.
patent: 6401082 (2002-06-01), Kropas-Hughes et al.
patent: 6421654 (2002-07-01), Gordon
patent: 6424961 (2002-07-01), Ayala
patent: 6507828 (2003-01-01), Leonard et al.
patent: 6532305 (2003-03-01), Hammen
patent: 6601049 (2003-07-01), Cooper
patent: 6687686 (2004-02-01), Nervegna et al.
patent: 6745169 (2004-06-01), Schlang et al.
patent: 6894639 (2005-05-01), Katz
patent: 6947915 (2005-09-01), Liang et al.
patent: 6965885 (2005-11-01), Gutta et al.
patent: 6968327 (2005-11-01), Kates et al.
patent: 6976012 (2005-12-01), Rising, III
patent: 7047225 (2006-05-01), Poon
patent: 7054850 (2006-05-01), Matsugu
patent: 7139740 (2006-11-01), Ayala
patent: 7287015 (2007-10-01), Cecchi et al.
patent: 7459432 (2008-12-01), Cowley et al.
Toward Unification of Source Attribution Processes and Techniques, Khosmood, F.; Levinson, R.; Machine Learning and Cybernetics, 2006 International Conference on Digital Object Identifier: 10.1109/ICMLC.2006.258376 Publication Year: 2006 , pp. 4551-4556.
Using the particle swarm optimization technique to train a recurrent neural model, Salerno, J.; Tools with Artificial Intelligence, 1997. Proceedings., Ninth IEEE International Conference on Digital Object Identifier: 10.1109/TAI.1997.632235 Publication Year: 1997 , pp. 45-49.
Hybrid system for robust recognition of noisy speech based on evolving fuzzy neural networks and adaptive filtering, Kasabov, N.; Illiev, G.; Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on vol. 5 Digital Object Identifier: 10.1109/IJCNN.2000.861440 Publication 2000 , pp. 91-96 vol. 5.
An adaptive function neural network (ADFUNN) for phrase recognition, Miao Kang; Palmer-Brown, D.; Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on vol. 1 Digital Object Identifier: 10.1109/IJCNN.2005.1555898 Publication Year: 2005 , pp. 593-597 vol. 1.
Levitan, Irwin B. and Kaczmarek, Leonard K., The Neuron: Cell and Molecular Biology, Third Edition, ISBN: 0-19-514523-2, 2002, 603 Pages, Oxford University Press, U.S.A.
Anil K. Jain, Jianchang Mao, K.M. Mohiuddin, “Artificial Neural Networks: A Tutorial,” Computer, vol. 29, No. 3, pp. 31-44, Mar., 1996.
William P. Jones, Josiah Hoskins, “Back-Propagation, A generalized delta learning rule,” Byte, Oct. 1987, pp. 155-162, vol. 12, No. 11, McGraw-Hill.
DARPA, Autonomous Ground Vehicle Grand Challenges for 2004 through 2006, Internet http://www.darpa.mil/grandchallenge/overview.asp.
Douglas Eck, “Recurrent Neural Networks—A Brief Overview”, Oct. 1, 2007, University of Montreal.
Dominic John Repici, “Netlab format A0 version (NLA001)”, Apr. 2, 1990, http://www.JohnRepici.com/NN/.
LandOfFree
Feedback-tolerant method and device producing... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Feedback-tolerant method and device producing..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Feedback-tolerant method and device producing... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4209710