Artificial Neural Networks are a widely used paradigm for Artificial Intelligence, with applications ranging from weather prediction, image processing, and time series analysis, to materials science and technology, concrete technology, and metallurgy.
n many of these cases, the generalization ability of the network is influenced by bias or subjectivity on the division of the data (a critical phase of the application of the methodology), that is usually compensated by repeated use or cross-validation.
Moreover, many of the applications of Neural Networks to concrete, welding, and other similar technologies are limited by the fact that most of these tools do not provide an error estimation, making its use in real life complicated.
The present project is aimed at developing a set of tools to address these issues, limiting bias and subjectivity in data division, making the most out of the data available, and providing error estimates of the prediction given by the network.
Complementary Methods for Neural Networks
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.
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.