Method
- Divide the available data into training and validation sets.
- Use a large number of hidden units.
- Use very small random initial values.
- Use a slow learning rate.
- Compute the validation error rate periodically during training.
- Stop training when the validation error rate "starts to go up".
It is crucial to realize that the validation error is not a good estimate of the generalization error. One method for getting an unbiased estimate of the generalization error is to run the net on a third set of data, the test set, that is not used at all during the training process. The error on the test set gives estimate on generalization; to have the outputs of the net approximate target values given inputs that are not in the training set.
Read more about this topic: Early Stopping
Famous quotes containing the word method:
“It is to be lamented that the principle of national has had very little nourishment in our country, and, instead, has given place to sectional or state partialities. What more promising method for remedying this defect than by uniting American women of every state and every section in a common effort for our whole country.”
—Catherine E. Beecher (1800–1878)
“I have a new method of poetry. All you got to do is look over your notebooks ... or lay down on a couch, and think of anything that comes into your head, especially the miseries.... Then arrange in lines of two, three or four words each, don’t bother about sentences, in sections of two, three or four lines each.”
—Allen Ginsberg (b. 1926)
“There is assuredly no more effectual method of clearing up one’s own mind on any subject than by talking it over, so to speak, with men of real power and grasp, who have considered it from a totally different point of view.”
—Thomas Henry Huxley (1825–95)