Signal processing apparatus having at least one neural network h

Details Signal processing apparatus having at least one neural network h Signal processing apparatus having at least one neural network h

1992-01-24

1993-11-02

Fleming, Michael R.

395 23, 395 24, 395 27, 395 61, G06F 1518

Patent

active

052590640

ABSTRACT:
A signal processing apparatus for controlling an object includes an input unit, a neural network, an output unit, a teaching unit, and an error signal generator for generating a teaching signal that makes the neural network learn in real time. An error signal generator generates an error signal from the teaching signal and information contained in the network output signal. The error signal controls the neural network so that the control output signal has correct control information with respect to the output signal from the controlled object.

REFERENCES:
patent: 4858147 (1989-08-01), Conwell
patent: 4893255 (1990-01-01), Tomlinson, Jr.
patent: 4912655 (1990-03-01), Wood
patent: 5005206 (1991-04-01), Naillon et al.
patent: 5058033 (1991-10-01), Bonissone et al.
patent: 5086479 (1992-02-01), Takenaga
patent: 5093899 (1992-03-01), Hiraiwa
patent: 5095443 (1992-03-01), Watanabe
patent: 5131073 (1992-07-01), Furuta et al.
patent: 5140530 (1992-08-01), Guha et al.
patent: 5140670 (1992-08-01), Chua et al.
patent: 5142612 (1992-08-01), Sharik
patent: 5157738 (1992-10-01), Carpenter et al.
patent: 5182794 (1993-01-01), Gasperi et al.
Andrew G. Barto, Richard S. Sutton, and Charles W. Anderson "Neuronlike Adaptive Elements That Can Solve Difficult Learning Control Problems" IEEE Transactions on Systems, Sep. 1983, 834-846.
T. Fukuda, T. Shibata, M. Tokita, T. Mitsuoka Nagoya University, Dept. of EE. Furo-Cho 1, Chikusa-Ku, Nagoya, 464-01, Japan, pp. 447-451.
Paulo Gaudiano and Stephen Grossberg, "Vector Associative Maps . . . Movement Trajectories," Neural Networks, vol. 4, pp. 147-183, 1991.
Ito et al., "A Neural Network Model Extracting Features from Speech Signals", vol. J70-D, No. 2 Feb. 1987--The Transactions of the Institute of Electronics, Information and Communication Engineers.
A. F. Murray et al., "Asynchronous Arithmetic for VLSI Neural Systems", Electronics Letters, vol. 23, No. 12, Jun. 4, 1987, pp. 642-643.
A. F. Murray et al., "A Novel Computational and Signalling Method for VLSI Neural Networks", ESSCIRC '87, Thirteen European Solid-State Circuits Conference, Sep. 23-25, 1987, pp. 19-22.
K. Kamada et al., "Digital Neuron Model", 1990 Spring National Convention Record D-3, The Institute of Electronics and Communication Engineers, 1988, pp. 2-3.
T. Yoshida et al., "Neuron Coupling Model", 1974 National Convention Record S9-7, The Institute of Electronics and Communication Engineers, pp. 248-251.
K. Fukushima, "Multiple-Layer Circuit Having Self-Organizing Function--Cognitron", 1974, National Convention Record S9-7, The Institute of Electronics and Communication Engineers, p. 250.
K. Fukushima, "Improvement in Pattern-Sensitivity of Cognitron", The Transactions of the Institute of Electronics and Communication Engineers, vol. J62-A, No. 10, pp. 650-657.
W. Banzhaf, "On a Simple Stochastic Neuron-Like Unit", Biological Cynbernetics, vol. 60, No. 2, 1988, pp. 153-160.

Affiliated with

Also associated with

Rating

Signal processing apparatus having at least one neural network h does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Signal processing apparatus having at least one neural network h, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Signal processing apparatus having at least one neural network h will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1764082