Available Master topics: Machine Learning

Memorability concept has been mostly investigated on the images using Machine Learning [1]. However, there is no measure available in the literature that can assess the difficulty of remembering a given password (word) or number.

What we want to find out is whether machine learning can be trained to create an appropriate CAD model from only the Lidar point cloud, or a Lidar point cloud with some images, if it has been trained with CAD reconstructions that have been created by humans using all the methods mentioned above.

Cardiovascular diseases are burdening the healthcare systems and the costs are expected to rise in the years to come. Acute stroke alone is estimated to cost the European countries an overwhelming 40 billion annually.


The aim of the project is to obtain a deeper understanding of GANs and develop new models and estimation techniques with improved properties.

In this project, we suggest a third option namely to use Generative Adversarial Models (GANs) to generate artificial, but realistic images of faces.
The generated images will be used as survey images of real candidates in Brazilian elections

The current state-of the-art of machine learning adopts the use of batch learning where the data is available offline, mostly divided into test and training sets.

The massive increase in the incidence of diabetes is now a major global healthcare challenge, and the treatment of diabetes is one of the most complicated therapies to manage, because of the difficulty in predicting blood glucose (BG) levels of diabetic patients.

In this project the goal is to explore existing state of the art methods from machine learning and statistics such as Recurrent neural networks, ARMA and Long short term memory networks.

In this project, a simple environment for the emergence of general intelligence features will be investigated, where agents can evolve through environmental rewards, and learn throughout their lifetime. The chosen control system for agents is spiking neural networks.

Vast amounts of data is being collected to assess the reliability and performance of mobile broadband network and needs to be processed in order to understand the potential causes of failures [1, 2]. We started collecting this data in 2013 and it amounts to over 13 TB in volume.

Performance of many algorithms in machine learning crucially depends on one or more tuning parameters. At the same time, the issue of parameter selection and tuning still remains a big challenge for most real-life applications.

Myocardial ischemia due to coronary artery occlusion promotes cardiac tissue remodeling that increases patient risk to lethal arrhythmias and sudden cardiac death (SCD). However, determining individual patient risk to SCD remains difficult and often involves invasive techniques.