System, for learning an external evaluation standard

Details System, for learning an external evaluation standard System, for learning an external evaluation standard

1992-10-14

1995-05-30

Downs, Robert W.

Boots, shoes, and leggings

364148, 395 22, 395 81, G06F 1518

Patent

active

054209641

ABSTRACT:
This invention pertains to neural network system for learning an external evaluation standard and for learning the evaluation from the outside for the processing result, in a system capable of internal evaluation of the correspondence between external information and the processing result of its own system for the input information. It purports to learn the external evaluation as the internal evaluation standard of the internal evaluation time. The learning system comprises an internal evaluation unit for evaluating an evaluation input pattern including input information at a first point in time and input information inputted at a point in time for the processing result of its own system for the input information according to the internal evaluation standard at a system execution time; and an evaluation desired pattern memory unit for making the external evaluation correspond with the evaluation input pattern and for memorizing it as an evaluation desired pattern for having the internal evaluation unit learn the external evaluation standard. The system is configured to have an internal evaluation unit to learn the evaluation desired pattern at a learning time of the system. This system is applicable in a robot control system.

REFERENCES:
patent: 4884216 (1989-11-01), Kuperstein
patent: 4933871 (1990-06-01), De Sieno
Barto et al., "Neuronlike Adaptive Elements That Can Solve Difficult Learning Control Problems", IEEE Trans. on Systs., Man, and Cybernetics, vol. SMC-13(5), 1983, pp. 834-846.
Hale, F. J., Intro. to Control System Analysis and Design, Prentice-Hall, Inc., 1973, pp. 1-23.
Miller, W. T., "Real-Time Application of Neural Networks for Sensor-Based Control of Robots with Vision", IEEE Trans. Syst. Man, and Cybernetics, vol. 19 (4) 1989, pp. 825-831.
Bock et al, "The Project Alias: an Application of Collective Learning Systems Theory to an Adaptive Learning Image Analysis System", International Workshop of Neural Networks & Their Applications, pp. 407-427, Nov. 1989.
Agrawala, "Learning with Various Types of Teachers", Proceedings of the First International Joint Conference on Pattern Recognition 30, pp. 453-461, Oct. 30-Nov. 1, 1973.
Kosko, "Unsupervised Learning in Noise", IJCNN International Joint Conference on Neural Networks, pp. 7-17, Jun. 1989.
Ritter, et al, "Topology-Conserving Maps for Learning Visuo-Motor Coordination", Neural Networks, pp. 159-168, vol. 2, No. 3, 1989.
Bock, "A Natural Paradigm for Artificial Intelligence: Collective Learning Systems Theory", The Second International Conference on Computers and Applications, pp. 30-37, Jun. 1987.
European Search Report, The Hague, search completed Dec. 3, 1992.
Pourboghart et al., "Neural Network Models for the Learning Control of Dynamical Systems with Application to Robotics", Lect. Notes in Control, Springer Verlag, 1989, pp. 50-60.
McClelland et al., Explorations in Parallel Distributed Processing, MIT Press, 1988, pp. 1-3, 137-150.
Psaltis et al., "A Multilayered Neural Network Controller" IEEE Control Syst. Mag., Apr. 1988, pp. 17-21.
Elsley, R. K., "A Learning Architecture for Control Based on Back-Propagation Neural Networks" Proc. IEEE Intl. Conf. Neural Networks, 1988, pp. II 587-II 594.
Kung et al., "Neural Network Architectures for Robotic Applications," IEEE Trans. Robotics & Automation, Oct. 1989, pp. 641-657.
Franklin, J. A., "Refinement of Robot Motor Skills Through Reinforcement Learning", Proc. 27th Conf. Decision and Control, Dec. 1988, 1096-1101.
Williams, R. J., "On the Use of Backpropagation in Associative Reinforcement Learning", Jul. 1988, IEEE Conf. on Neural Networks, I-263-I-270.
Jameson, J., "A Neurocontroller Based on Model Feedback and the Adaptive Heuristic Critic", 1990 IEEE Conf. on Neural Networks, II, 37-44.
Werbos, P. J., "Backpropagation and Neurocontrol: A Review and Prospectus", IJCNN, Jun. 1989, I-209-I-216.
Leaver et al., "Stochastic Computing and Reinforcement Neural Networks", First IEE Intl. Conf. on Artificial Neural Networks, Oct. 1989, 163-170.

Affiliated with

Also associated with

Rating

System, for learning an external evaluation standard does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with System, for learning an external evaluation standard, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System, for learning an external evaluation standard will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-368839