Data processing: artificial intelligence – Neural network – Learning task
Reexamination Certificate
2011-02-22
2011-02-22
Starks, Jr., Wilbert L (Department: 2129)
Data processing: artificial intelligence
Neural network
Learning task
C706S045000
Reexamination Certificate
active
07895140
ABSTRACT:
It is possible to acquire existing techniques in a neural network model currently studied and developed so as to generalize them as an element technique, and provide modeling of a basic unit of bottom-up approach using the neural network by adding new values to the existing techniques. A network learning device builds up a network of basic units in a network section, acquires an input from a sensor input section for evaluating it, changes a coupling weight coefficient by using a correlation operation so that the evaluation value satisfies a predetermined evaluation value, and inserts a new neural network according to need.
REFERENCES:
patent: 2006/0184467 (2006-08-01), Nagashima
patent: 9-91263 (1997-04-01), None
patent: 2004/033159 (2004-04-01), None
patent: WO-2004/104917 (2004-12-01), None
Chan, et al, A Joint Compression-Discrimination Neural Transformation Applied to Target Detection, IEEE Transactions on Systems, Man, and Cybernetics—Part B: Cybernetics, vol. 35, No. 4, Aug. 2005, pp. 670-681.
Eberhart, et al, Early Neural Network Development History: The Age of Camelot, IEEE Engineering in Medicine and Biology, Sep. 1990, pp. 15-18.
Elman, Jeffrey, L., et al, Chapter 2: Why Connectionism?, Rethinking Innateness: A Connectionist Perspective on Development, 1996, pp. 47-106.
Written Opinion of the International Searching Authority (Form PCT/ISA/237) of International Application No. PCT/JP2006/310119 having an International filing date of May 22, 2006.
International Search Report of PCT/JP2006/310119, date of mailing Jul. 4, 2006.
“Extended European Search Report”, mailed by EPO and corresponding to European application No. 06756425.2 on Jul. 27, 2010.
Bonaiuto, James et al., Recognizing Invisible Actions Proceedings of the International Workshop Modeling Natural Action Selection (MNAS)section 2.3; Figure 2, Jul. 25, 2005, pp. 113-120.
Dauce, E, “Learning and control with large dynamic neural networks” The European Physical Journal—Special Topics, vol. 142, No. 1, section 2.2, Introduction, paragraphs 5-6, Mar. 2007, pp. 123-161.
Harvey, Inman Learning and CTRNNs Workshop on a Dynamical Systems Approach to Life and Cognition slides 5, 6, 18, 19, Mar. 8, 2005.
Maeda, Yutaka et al., “Bidirectional associative memory with learning capability using simultaneous perturbation” Neurocomputing vol. 69, No. 1-3, Aug. 26, 2005, pp. 182-197.
McHale, Gary et al., Quadrupedal Locomotion: GasNets, CTRNNs and Hybrid CTRNN/PNNs Compared Proceedings of the 9th International Conference on the Simulation and Synthesis of Living Systems (ALIFE9) the whole document Sep. 12, 2004, pp. 106-112.
Nagashima, Fumio A Motion Learning Method using CPG/NP section 1, last paragraph; figure 2, section 3.2, last paragraph; figure 7 section 4.2, appendix A; figure 11 Aug. 17, 2006.
Righetti, Ludovic et al., “Dynamic Hebbian learning in adaptive frequency oscillators”, Physica D, vol. 216, No. 2 sections 1, 2.1.2, 5, Apr. 15, 2006, pp. 269-281.
Fujitsu Limited
Fujitsu Patent Center
Starks, Jr. Wilbert L
LandOfFree
Neural network learning device, method, and program does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Neural network learning device, method, and program, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network learning device, method, and program will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2619830