Colloquium Computer Science, Prof.dr. C.N. Schizas, University of Cyprus

Title: Variable target values Neural Network for dealing with imbalanced datasets

                           

Abstract:

A classification algorithm is proposed for dealing with highly imbalanced datasets that often appear in biomedical problems. Its idea comes from the way a neural network is trained in order to get a decent hypothesis out of a dataset that comprises a huge sized majority class and a tiny size minority class. This situation is especially probable when forming machine learning databases describing rare medical conditions. The algorithm is tested on a large dataset for predicting the risk of preeclampsia in pregnant women and preliminary results are encouraging. Conventional machine learning algorithms tend to provide poor hypothesis for extremely imbalanced datasets by favoring the majority class. The proposed algorithm is not trained on the basis of the mean squared error objective function and thus avoids the overwhelming effect of the highly asymmetric class sizes.

Colloquium coordinators are Prof.dr. M. Aiello (e-mail : M.Aiello rug.nl ) and
Prof.dr. M. Biehl (e-mail: M.Biehl rug.nl )

http://www.rug.nl/research/jbi/news/colloquia/computerscience