Patent
1990-12-18
1992-11-24
MacDonald, Allen R.
395 27, G06F 1518
Patent
active
051670062
ABSTRACT:
A neuron unit processes a plurality of input signals and outputs an output signal which is indicative of a result of the processing. The neuron unit includes input lines for receiving the input signals, a forward process part including a supplying part for supplying weight functions and an operation part for carrying out an operation on each of the input signals using one of the weight functions and for outputting the output signal, and a self-learning part including a generating part for generating new weight functions based on errors between the output signal of the forward process part and teaching signals and a varying part for varying the weight functions supplied by the supplying part of the forward process part to the new weight functions generated by the generating part.
REFERENCES:
patent: 3293609 (1966-12-01), Martin
patent: 3601811 (1971-08-01), Yoshino
patent: 4193115 (1980-03-01), Albus
patent: 4807168 (1989-02-01), Moopenn et al.
patent: 4893255 (1990-01-01), Tomlinson, Jr.
patent: 4918618 (1990-04-01), Tomlinson, Jr.
patent: 4941122 (1990-07-01), Weideman
patent: 4974169 (1990-11-01), Engel
patent: 4990838 (1991-02-01), Kawato et al.
patent: 5043913 (1991-08-01), Furutani
A General Purpose Digital Architecture for Neural Network Simulations; Duranton et al; First IEEE Inter. Conf. on Artificial Neural Networks; 16-18, Oct. 1989; pp. 62-66.
Design of Parallel Hardware Neural Systems from Custom VSLI `Building Block` Chips; Eberhardt et al; IJCNN; Jun. 18-22, 1989; vol. 2; pp. 183-190.
An Analog CMOS Backward Error-Propagation LSI; Furman et al; First Annual Inns Symposium; Sep. 1988.
The VLSI Implementation of Stonn; Wilke et al; IJCNN 1990; vol. 2; pp. 593-598.
Asynchronous VLSI Neural Networks Using Pulse-Stream Arithmetic; Murray et al; IEEE Journal of Solid-State Circuits; vol. 23, No. 3; Jun. 1988, pp. 688-697.
A Study of Regular Architectires for Digital Implementations of Neural Networks; Suzuki et al; IEEE Inter. Symposium on Circuits and Systems; May 8-11, 1989; pp. 82-85.
VLSI Architectures for Neural Networks; Treleaven et al; IEEE Micro; Dec. 1989; pp. 8-27.
Digital Neural Networks; Martinez; Proc. of the 1988 IEEE Inter. Conf on Systems, Man, & Cybernetics; Aug. 8-12, 1988; pp. 681-684.
Layered Neural Nets for Pattern Recognition; Widrow et al; IEEE Trans. on Acoustics, Speech, and Signal Processing; vol. 36, No. 7; Jun. 1988; pp. 1109-118.
A Wafer Scale Integration Neural Network Utilizing Completely Digital Circuits; Yasunaga et al; Proc. of the IJCNN; Jun. 18, 1989; vol. 2, pp. 213-217.
Yuzo Hirai et al, "Design of a Completely Digital Neuro-Chip," Integrated Circuit Study Group of the Electronic Information Communication Society, Dec. 16, 1988, pp. 89-93.
W. Banzhaf, "On a Simple Stochastic Neuron-Like Unit," Biol. Cybern., 1988, pp. 155-160.
Ebi Yutaka
Eguchi Hirotoshi
Furukawa Tatsuya
Furuta Toshiyuki
Horiguchi Hiroyuki
MacDonald Allen R.
Ricoh & Company, Ltd.
LandOfFree
Neuron unit, neural network and signal processing method does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Neuron unit, neural network and signal processing method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neuron unit, neural network and signal processing method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-928848