Patent
1990-02-20
1992-07-07
MacDonald, Allen R.
G06F 1518
Patent
active
051290383
ABSTRACT:
An improved iterative learning machine having a plurality of multi-input/single-output signal processing units connected in a hierarchical structure includes a weight coefficient change control unit which controls weight change quantities for those multi-input/single-output signal processing units having iteratively reduced errors thereby increasing the learning speed, contrary to conventional learning machines which perform a learning operation in order to minimize a square error of multi-input/single-output signal processing units in the highest hierarchy of the hierarchical structure.
REFERENCES:
patent: 3601811 (1971-08-01), Yoshino
patent: 4912649 (1990-03-01), Wood
patent: 4912654 (1990-03-01), Wood
D. E. Rumelhart, G. E. Hinton and R. J. Williams: "Learning Representations by Back-Propagating Errors", Nature, vol. 323, pp. 533-536, Oct. 9, 1986.
Lippmann, "An Introduction to Computing with Nueral Nets", IEEE Acoustics, Speech, and Signal Processing Magazine, pp. 4-22, Apr. 1987.
Widrow, "Punish/Reward: Learning with a Critic in Adaptive Threshold Systems", IEEE Transactions on Systems, Man and Cybernetics, vol. SMC3, No. 5, pp. 455-465, Sep. 1973.
Kohda Toshiyuki
Sakaue Shigeo
Shimeki Yasuharu
Yamamoto Hiroshi
MacDonald Allen R.
Matsushita Electric - Industrial Co., Ltd.
LandOfFree
Neural network with selective error reduction to increase learni 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 with selective error reduction to increase learni, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network with selective error reduction to increase learni will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1836126