Method of enhancing the selection of a training set for use in t

Details Method of enhancing the selection of a training set for use in t Method of enhancing the selection of a training set for use in t

1994-07-29

1996-09-24

Davis, George B.

395 22, 395 24, G06F 700

Patent

active

055599290

ABSTRACT:
A method for enhancing the performance of an artificially intelligent system employing a neural network by proving an optimized training set for training the neural network. The optimized training set is produced by identifying and permanently removing inaccurate training pairs in the training set. The permanent removal of inaccurate training pairs is performed in a worst-error order.

REFERENCES:
patent: 4782460 (1988-11-01), Spencer
patent: 4875183 (1989-10-01), Graf et al.
patent: 4885757 (1989-12-01), Provence
patent: 5255362 (1993-10-01), Brandstetter et al.
Zhang et al, "Error Back Propagation with Minimum-Entropy Weights", IEEE Int. Conf. on Neural Networks, 1991.
Lee et al, "An Efficient Hidden Node Reduction Technique for Multilayer Perceptrons" IEEE Int. Conf. on Neural Networks, 1991.
Hergert et al, "A Comparison of Weight Elimination Methods for Reduction Complexity in Neural Networks", IEEE Int. Conf. on Neural Networks, 1992.
Hassibi et al, "Optimal Brain Surgeon and General Network Pruning" IEEE Int. Conf. on Neural Network, 1993.
Reed et al, "Pruning Algorithm--A Survey", IEEE Transactions on Neural Networks, vol. 4, No. 5, Sep. 1993.
Specht et al, "A General Regression Neural Network" IEEE Transactions on Neural Networks, vol. 2, No. 6, Nov. 1991.
Sietsma et al, "Neural Net Pruning--Why and How", IEEE Int. Conf. on Neural Networks, 1988.
Martinez et al, "A Simple Strategy for Building and Training Multi-layer Neural Networks" IEEE Int. Conf. on Neural Networks, 1991.
Jiang et al, "Compact Polynomial Modeling of the Multi-layer Perceptron", 26th Asilomar Conf. on Signals, System & Computers, 1992.
Yang et al, "A Convenient Method to Prune Multilayer Neural Networks via Transform Domain Backpropagation Algorithm", IEEE Int. Conf. on Neural Networks, 1992.

Affiliated with

Also associated with

Rating

Method of enhancing the selection of a training set for use in t does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method of enhancing the selection of a training set for use in t, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of enhancing the selection of a training set for use in t will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1946938