Output of pnd_cv application. |
Output format of the application for training and testing PND ensembles using cross-validation techniques.
The application print on standard output the following informations:
- General information about cross-validation: number of folds, number of classes.
- Type of Output Coding decomposition and number of dichotomizers
- Structure of dichotomizers: number of hidden layers, hidden units, inputs.
- Type of learning algorithm, its parameters and stop conditions.
- Training results for each fold: for each base learner of the ensemble is returned its normalized RMS error and number of iterations.
- Testing results for each fold: number of errors and error rate.
- Overall results of cross-validation: Number of errors and error rate , confusion matrix
- Elapsed CPU time
See also pnd_cv
Example:
Alphabetic index Hierarchy of classes