Bachelor and Master Theses

in this project, the student(s) will have the freedom to investigate different deep learning techniques, including convolutional neural network, LSTM, gated recurrent network, graphical neural network, etc. 

They will develop a prediction model by adopting and customising the most suitable learning technique or build a hybrid model by skillfully integrating different approaches, then implement and evaluate their model.

If two students apply, the model should also be deployed as a hardware / software solution applying specific constraints.

Academic Background

1. A solid understanding of digital systems engineering principles.

2. Basic knowledge of machine learning, hardware / software embedded system implementation. 

3. Prior coursework on embedded systems, machine learning / AI.

4. Proficiency in English, both spoken and written.

Technical Skills

1. Familiarity with tools such as Matlab and Simulink.

2. Experience with programming languages such as Python.

Activities are part of the EU project RENEW.

***

Targeted number of students: 2. If less than 2, tasks will be adapted.