Patent
1994-07-14
1998-11-24
Hafiz, Tariq R.
395 3, 395 50, 395 61, G06F 1518
Patent
active
058419497
ABSTRACT:
Provided is a learning method for artificial intelligence which includes a first step of dividing a multidimensional curved surface constituted by fact data into a plurality of regions; and a second step of generating wiring functions of the respective divisional regions, and storing the wiring functions as a knowledge base. In order to carry out the above method, provided is a learning apparatus for artificial intelligence which includes a fact data storage device for storing fact data; a region dividing device for dividing, into a plurality of regions, a multidimensional curved surface composed by the data stored in the fact data storage device; a regional space wiring function generating device for generating wiring functions of the respective divisional regions divided by the region dividing device; and a wiring function data base for storing the generated wiring functions as a knowledge base.
REFERENCES:
patent: 5249257 (1993-09-01), Akahori et al.
Powell, M.J.D. "Radial Basis Functions for Multivariable Interpolation: A Review." Algorithnms for Approximations. J.C.Mason and M.G. Cox, eds. Oxford University Press, Oct. 1985.
Freund, Rudolf J., and William J. Wilson. "Statistical Methods." Academic Press, Jan. 1993.
Kuo, R.J., P.H. Cohen, and S.R.T. Kumara. "Neural Network Driven Fuzzy Inference System." Nueral Networks, 1994 International Conference.
Moody, John and Christian J. Darken. "Fast Learning in Networks of Locally-Tuned Processing Units" Neural Computation. pp. 117-123, Oct. 1988 .
Chikahisa Takemi
Nakaya Jun
Addin Research Inc.
Hafiz Tariq R.
LandOfFree
Learning/inference method for artificial intelligence and appara does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Learning/inference method for artificial intelligence and appara, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning/inference method for artificial intelligence and appara will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1712506