encog-java-core
encog-java-core copied to clipboard
Allow strategies to be specified for Encog Workbench GUI Training
Now that Issue #28 has been added, it would be very nice to be able to add regularization, and other strategies to the workbench training. This should be added to the training dialog. Related to Issue #97.
Since SVM already supports regularization, perhaps a general algorithm to search for optimal regularization parameter(s) may be used once "SVM Search" is enhanced (issue #54). I also see splitting data into 3 dataset (for training, cross validation and testing) important as well.