Patent
1994-03-07
1996-04-02
Downs, Robert W.
395 27, G06F 1518
Patent
active
055048382
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 an error signal representing an error between the output signal of the forward process part and a teaching signal 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. The error signal includes first and second error signal components representing pulse densities.
REFERENCES:
patent: 3293609 (1966-12-01), Martin
patent: 3358271 (1967-12-01), Marcus et al.
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
patent: 5048100 (1991-09-01), Kuperstein
patent: 5093899 (1992-03-01), Hiraiwa
patent: 5095443 (1992-03-01), Watanabe
patent: 5129038 (1992-07-01), Kodha et al.
patent: 5165010 (1992-11-01), Masuda et al.
Ito et al., "A Neural Network Model Extracting Features form Speech Signals", Electronic Information Communication Society Papers '87/2 vol. J70-D No. 2.
Murray et al., "Asynchoronous Arithmetic for VLSI Neural Systems", Electronic Letters 4th Jun. 1987, vol. 23, No. 12.
Murray et al., "A Novel Computational and Signalling Method for VLSI Neural Networks", Digest of Technical Papers ESSCIRC '87 Thirteenth European Solid-State Circuits Conference, Sep. 23-25, 1987.
Kamada et al., "Digital Neuron Model", 1988 Electronic Information Communication Society Spring National Conference.
Yoshida et al., "Neural Coupling Model of Visuel Domain", 1974 Electronic Communication Society National Conference.
K. Fukushima, "Cognitron", 1974 Electronic Communication Society National Conference.
K. Fukushima, "Improvement in Pattern-Selectivity of a Cognitron", Electronic Communication Society Papers '79/10 vol. J62-A No. 10.
W. Banzhaf, "On a Simple Stochastic Neuron-Like Unit", Biological Cybernetics vol. 60, No. 2, 1988.
Martinez, T., "Digital Neural Networks", Proceedings of the 1988 IEEE Conference on Systems, Man and Cybernetics, Aug. 8-12, 1988, pp. 681-684.
Widrow, B., et al., "Layered Neural Nets for Pattern Recognition", IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 36, No. 7, Jul. 1988, pp. 1109-1118.
Yasunaga, M., et al., "A Wafer Scale Integration Neural Network Utilizing Completely Digital Circuits", Proc. of the IJCNN, Jun. 18, 1989, vol. 2, pp. 213-217.
Murray, A. F., and Smith, A. V. W., "Asynchronous VLSI Neural Networks Using Pulse-Stream Arithmetic", IEEE Journal of Solid-State Circuits, vol. 23, No. 3, Jun. 1988, pp. 688-697.
Suzuki, Y. and Atlas, L. E., "A study of Regular Architectures for Digital Implementation of Neural Networks", IEEE International Symposium on Circuits and Systems, 8-11 May 1989, pp. 82-85.
Treleaven, P., et al., "VLSI Architecture for Neural Networks", IEEE Micro, Dec. 1989, pp. 8-27.
Hirai, Yuzo 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.
Banzhaf, "On a Simple Stochastic Neuron-Like Unit", Biological Cybernetics., 60, 1988, pp. 155-160.
Duranton, M., et al., "A General Purpose Digital Architecture for Neural Network Simulations", First Conference on Artificial Neural Networks, 16-18 Oct. 1989, pp. 62-66.
Eberhardt, S. et al., "Design of Parallel Hardware Neural Network Systems from Custom Analog VLSI `Building Block` Chips", IJCNN, Jun. 18-22, 1989, vol. 2, pp. 183-190.
Furman, B., et al., "An Analog CMOS Backward Error-Propagation LSI", First Annual INNS Symposium, 1988.
Wike, W., et al., "The VLSI Implementation of STONN", IJCNN, 1990, vol. 2, pp. 593-598.
Tomberg, et al., "Fully Digital Neural Network Implementation Based on Pulse Density Modulation", IEEE 1989 Custom Integrated Circuits Conf., May 1989, 12.7.1-12.7.4.
T. Furuta et al., "Neuron Model Utilizing Pulse Density and its Self-Learning Circuit," 1990 Spring National Convention Record, The Institute of Electronics, Information and Communication Engineers, vol. D-56 (1990), pp. 6-56.
T. Furuta et al., "Pulse Density Neuron Model Having Learning Function and How to Construct it by Hardwares," Inst. Electronics, Infor. and Comm. Engr. (Oct. 15, 1990), p. 66.
T. Furuta et al., "Development of Neuro LSI with Self-Learing Function Utilizing Pulse Density," 1990 Autumn National Convention Record, The Institute of Electronics, Information and Communication Engineers, vol. D-41 (1990), pp. 6-41.
Ebi Yutaka
Eguchi Hirotoshi
Furukawa Tatsuya
Furuta Toshiyuki
Horiguchi Hiroyuki
Downs Robert W.
Ricoh & Company, Ltd.
LandOfFree
Neuron unit with error signal having components representing pul 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 with error signal having components representing pul, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neuron unit with error signal having components representing pul will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2022870