Error Analysis for Static Artificial Neural Networks


In recent years, the Classes Imbalance is recognized as the crucial problem for Machine Learning. This fact generates a slowness in the convergence of the minority classes. This project proposed a study of the Classes Imbalance in the Classification Problems to develop a set of heuristics algorithms based on modular Neural Networks and the data correction. In the way, we improve the convergence process and the generalization capacity of the Neural Network.
External link


Work with Us

We are always interested in new challenges and looking for new motivated people to work with.

If you are interested in colaborated with us, please contact us.

About Us

GITIA was founded on 2008 in order to promote and apply recent research works on advanced technologies to different of domains. Our main application areas cover collaborative work, decision-helping tools and distributed problem solving.