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:
“Traditional scientific method has always been at the very best 20-20 hindsight. It’s good for seeing where you’ve been. It’s good for testing the truth of what you think you know, but it can’t tell you where you ought to go.”
—Robert M. Pirsig (b. 1928)
“In child rearing it would unquestionably be easier if a child were to do something because we say so. The authoritarian method does expedite things, but it does not produce independent functioning. If a child has not mastered the underlying principles of human interactions and merely conforms out of coercion or conditioning, he has no tools to use, no resources to apply in the next situation that confronts him.”
—Elaine Heffner (20th century)
““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)