Ongoing Projects
PTDC/EIA-EIA/119004/2010: Deep architectures, such as neural networks with two or more hidden layers of units, are a class of machines that comprise several levels of non-linear operations, each expressed in terms of parameters that can be learned.
Completed Projects
POSC/EIA/56918/2004: 'EntNets - Entropic neural networks for the analysis of medical data', (2005-2008, 77k€), which was financed by FCT. The goal of the project was the development of neural networks using entropy as a cost function and their application to the analysis of medical data.
Events
* Organization of a special session on Transfer Learning at IWANN 2015 at Spain.
* Celebrating 25 years of INEB.