State space search system

Details State space search system State space search system

1992-09-17

1994-04-05

Fleming, Michael R.

395 13, G06F 1500

Patent

active

053012569

ABSTRACT:
A state space search system searches for an optimal goal state by searching in the direction of a steepest descent with respect to an evaluation function. When the search becomes impossible upon reaching a local minimum of the evaluation value, the evaluation value is increased to continue the search in the direction of steepest descent.

REFERENCES:
patent: 3214745 (1993-05-01), Sutherland
patent: 5078952 (1992-01-01), Gozani et al.
patent: 5119468 (1992-06-01), Owens
patent: 5148513 (1992-09-01), Koza et al.
patent: 5214715 (1993-05-01), Carpenter et al.
Dahl, Edward.; "Accelerated Learning using the Generalized Delta Rule"; IEEE First International Conference on Neural Networks; (FICNN) 21-24 Jun. 1987; pp. 523-530.
Almedia, Luis; "A learning rule for asynchronous perceptions with feedback in a combinatorial environment"; IEEE FICNN; 21-24 Jun. 1987; pp. 609-618.
Williams, Ronald J.; "A Class of Gradient-Estimating Algorithms for Reinforcement Learning in Neural Networks"; IEEE FICNN; Jun. 21-24 1987; pp. 601-608.
Hush, D. R. and Salas, J. M.; "Improving the Learning Rate of Back-Propagation with the Gradient Reuse Algorithm"; IEEE ICNN, Jul. 24-27 1988; pp. 441-446.
Vogl, T. P. and Mangis, J. K. and Rigler, A. K. and Zink, W. T. and Alkon, D. L.; "Accelerating the Convergence of the Back Propagation Method; Biological Cybermetics"; 1988; pp. 257-263.
Naifax; H. L.; Nasiruddin, M.; Sarrad. T.; "Effect of Weights on Back-Propagation and its Variations"; IEEE Int. Conf. On Systems, Man and Cybernotics; Nov. 14-17 1989; pp. 218-219.
Dajani, A. L. and Kamel, M. and Elmasvy, M. L.; "Gradient Methods in unsupervised Veunal Networks"; IEEE Int. Conf. on Neural Nets; Nov. 18-21 1991; pp. 1770-1775 vol. 2.
Edmonson, William; "Recursive Algorithm for State Space Spectrum Estimation", Fifth ASSP Workshop on Spectrum Estimation and Modeling; Oct. 10-12, 1990; pp. 265-269.
"Problem Space Search Using Steepest Descent Method"; S. Nakamura, Japanese Institute of Electrical Engineers, pp. 21-30, Sep. 30, 1991.
"Artificial Intelligence Handbook"; Artificial Intelligence Society of Japan; p. 27, Ohm-sha, 1990, Tokyo.

Affiliated with

Also associated with

Rating

State space search system does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with State space search system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and State space search system will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-518682