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:
“We have not given science too big a place in our education, but we have made a perilous mistake in giving it too great a preponderance in method in every other branch of study.”
—Woodrow Wilson (1856–1924)
“... [a] girl one day flared out and told the principal “the only mission opening before a girl in his school was to marry one of those candidates [for the ministry].” He said he didn’t know but it was. And when at last that same girl announced her desire and intention to go to college it was received with about the same incredulity and dismay as if a brass button on one of those candidate’s coats had propounded a new method for squaring the circle or trisecting the arc.”
—Anna Julia Cooper (1859–1964)
““I have usually found that there was method in his madness.”
“Some folk might say there was madness in his method.””
—Sir Arthur Conan Doyle (1859–1930)