Package Bio :: Package NeuralNetwork :: Module StopTraining :: Class ValidationIncreaseStop
[show private | hide private]
[frames | no frames]

Class ValidationIncreaseStop


Class to stop training on a network when the validation error increases.

Normally, during training of a network, the error will always decrease on the set of data used in the training. However, if an independent set of data is used for validation, the error will decrease to a point, and then start to increase. This increase normally occurs due to the fact that the network is starting to learn noise in the training data set. This stopping criterion function will stop when the validation error increases.
Method Summary
  __init__(self, max_iterations, min_iterations, verbose)
Initialize the stopping criterion class.
  stopping_criteria(self, num_iterations, training_error, validation_error)
Define when to stop iterating.

Method Details

__init__(self, max_iterations=None, min_iterations=0, verbose=0)
(Constructor)

Initialize the stopping criterion class.

Arguments:

o max_iterations - The maximum number of iterations that should be performed, regardless of error.

o min_iterations - The minimum number of iterations to perform, to prevent premature stoppage of training.

o verbose - Whether or not the error should be printed during training.

stopping_criteria(self, num_iterations, training_error, validation_error)

Define when to stop iterating.

Generated by Epydoc 2.1 on Sat Jul 16 15:49:03 2005 http://epydoc.sf.net