Applying Deep Learning with Weak and Noisy labels

In recent years, Deep Learning has achieved outstanding results outperforming previous techniques and even humans, thus becoming the state-of-the-art in a wide range of tasks, among which Computer Vision has been one of the most benefited areas.
Nonetheless, most of this success is tightly coupled to strongly supervised learning tasks, which require highly accurate, expensive and labor-intensive defined ground truth labels.
In this presentation, we will introduce diverse alternatives to deal with this problem and support the training of Deep Learning models for Computer Vision tasks by simplifying the process of data labelling or exploiting the unlimited supply of publicly available data in Internet (such as user-tagged images from Flickr). Such alternatives rely on data comprising noisy and weak labels, which are much easier to collect but require special care to be used.


Introduction to Graphs Learning

With the multimedia revolution more and more data has become available and easily accessible. Extracting useful information from this raw data is a complex and important task, so as to exploit it with advanced Machine Learning techniques.
Many important real-world datasets come in the form of graphs or networks, for which the classical problems to be addressed are: node classification, link prediction, community detection, and others. The main challenge is that the structure is very irregular if compared, for example, with images and applying some techniques is not a straightforward process.
In this presentation, we will introduce the advances in the field of graph learning in the last years, considerations, challenges and approaches.