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:
“Steady labor with the hands, which engrosses the attention also, is unquestionably the best method of removing palaver and sentimentality out of one’s style, both of speaking and writing.”
—Henry David Thoreau (1817–1862)
“You that do search for every purling spring
Which from the ribs of old Parnassus flows,
And every flower, not sweet perhaps, which grows
Near thereabouts into your poesy wring;
You that do dictionary’s method bring
Into your rhymes, running in rattling rows;”
—Sir Philip Sidney (1554–1586)
“The most passionate, consistent, extreme and implacable enemy of the Enlightenment and ... all forms of rationalism ... was Johann Georg Hamann. His influence, direct and indirect, upon the romantic revolt against universalism and scientific method ... was considerable and perhaps crucial.”
—Isaiah Berlin (b. 1909)