Graded learning device and method

Details Graded learning device and method Graded learning device and method

1988-12-21

1990-06-12

MacDonald, Allen

Boots, shoes, and leggings

364200, 3642766, G06F 1518

Patent

active

049338714

ABSTRACT:
A graded-learning processing network which grades its performance as it maps the input-output relationship during a training period. At the end of an operation of the Processing Newtork, its performance is graded and network variables are adjusted or amended, and the processing network is operated again and its performance is graded. The order or direction of performance grades (e.g. better or worse) are noted and the adjustments or amendments of the processing network may proceed in the same direction (or opposite direction) depending upon the grading of subsequent performances. This obviates the need for information about a desired response on output performance of the processing network at any given time, and is conducive to efficient learning for improved performance in a processing environment in which the operational parameters are not known.

REFERENCES:
patent: 4760604 (1988-07-01), Cooper et al.
S. F. Shapiro, Robotic Systems Learn Through Experience, Computer Design, Nov. 1, 1988, pp. 54-68.
T. Inglesby, No Clowning Around, Neural Networks Can Help Manufacturing, Manufacturing Systems, Oct. 1988, pp. 26-31.
H. H. Szu and R. L. Hartley, Nonconvex Optimization by Fast Simulated Annealing, vol. 75, No. 11, Proceedings of the IEEE 11, Nov. 1987, pp. 1538-1540.
H. Szu and R. Hartley, Fast Simulated Annealing, vol. 122, No. 3 & 4, Physics Letters A, Jun. 8, 1987, pp. 157-162.
D. H. Ackley, Stochastic Iterated Genetic Hillclimbing, Carnegie Mellon University Dissertation, CMU-CS-87-107, Mar. 1987, pp. 1-213.
G. E. Hinton, et al., Boltzman Machines: Constraint Satisfaction Networks that Learn, Carnegie Mellon University Technical Report, CMU-CS-84-119, May 1984, pp. 1-42.
A. G. Barto, et al., Neuronlike Adaptive Elements that Can Solve Difficult Learning Control Problems, vol. SCM-13, IEEE Transactions on Systems, Man, and Cybernetics, Sep./Oct. 1983, pp. 834-846.
A. G. Barto, et al., Associative Search Network: A Reinforcement Learning Associative Memory, 40 Biological Cybernetics, 1981, pp. 201-211.

Affiliated with

Also associated with

Rating

Graded learning device and 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 Graded learning device and method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Graded learning device and method will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-622321