Thesis offers

You are here

Check offers of other studies and specializations

Data Science and Computational Intelligence Knowledge Engineering and Machine Learning Modelling, Reasoning and Problem Solving

This project is a continuation of 2 previous master thesis. In the framework of the Paris 2024 Olympic Games Weather Project, leaded by TriM company, a big amount of data is being collected either on the sea through real time sensors during trainings and racings or from numerical weather prediction models. These data are being stored into a cloud database. Indeed sailing strategy and performance are strongly related with environmental features such as weather conditions, oceanic current and geography.

Knowledge Engineering and Machine Learning

In this project, we wish to create a summarized universal representation of packet flows within a computer network. We approach this problem as an Unsupervised Learning problem, where the summarized representation must be as small as possible while minimizing the reconstruction error. In order to build this representation, multiple approaches are to be considered. This includes using traditional techniques such as a Fourier Transformation, and using representations learned Machine Learning models, specifically Autoencoders and sequence models like 1-dimensional CNNs, RNNs

Knowledge Engineering and Machine Learning

To date, traditional Deep Learning (DL) solutions (e.g. Feed-forward Neural Networks, Convolutional Neural Networks) have had a major impact in numerous fields, such as Speak Recognition (e.g., Siri, Alexa), Autonomous driving, Computer Vision,etc. It was just recently, however, that a new DL technique called Graph Neural Network (GNN) was introduced, proving to be unprecedentedly accurate to solve problems that are formalized as graphs.

Data Science and Computational Intelligence Knowledge Engineering and Machine Learning

Recent advances in the field of Reinforcement Learning (DRL) are rising a lot of attention due to its potential for automatic control and automatization. Breakthroughs from academia and the industry (e.g, Stanford, DeepMind and OpenAI) are demonstrating that DRL is an effective technique to face complex optimization problems with many dimensions and non-linearities. However, to train a DRL agent in large optimization scenarios still remains a challenge due to the computational intensive operations during backpropagation.

This project aims to analyze the prediction capability of Optical Coherence Tomography Angiography (OCTA) images for Diabetes Mellitus (DM) and Diabetic Retinopathy (DR,) in a large high-quality image dataset from previous research projects carried out in the field of Ophthalmology (Fundacio¿ La Marato¿ TV3, Fondo Investigaciones Sanitarias, FIS). OCTA is a newly developed, non-invasive, retinal imaging technique that permits adequate delineation of the perifoveal vascular network. It allows the detection of paramacular areas of capillary non perfusion and/or enlargement of the foveal avascular zone (FAZ), representing an excellent tool for assessment of DR.

Data Science and Computational Intelligence Vision, Perception and Robotics. Assistive Technologies Hot Topics in AI and Professional Practice

Apply diffusion-based image generative models to convert videos into a cartoon style (e.g. from a sample image or a descriptive text). Depending on the obtained results a dictionary of styles may be created.

The student will have to implement different learning algorithms of Restricted Boltzmann Machine (RBM) neural networks using CUDA, and compare the performance against a standard CPU implementation.

Study and development of a Reinforcement Learning system for the automatization of dwelling plan generation in the architecture domain

Data Science and Computational Intelligence Vision, Perception and Robotics. Assistive Technologies

Training neural networks require large quantities of annotated data. Obtaining these data is expensive and labor-intensive. In this project, methods that use a mix of annotated and non-annotated data for semi-supervised training of object detectors will be studied. The work will be centered on using transformer architectures that use attention mechanisms.

Vision, Perception and Robotics. Assistive Technologies

Sports analytics is a key technology in professional and amateur sports. In this project, the goal is to develop a method to track the players in team games (basketball, football, ...) during the complete game. Because of the high amount of occlusions, the approach will be based strongly on improving reidentification methods and on graph methods to make an optimal assignment of tracks.

Hot Topics in AI and Professional Practice

The objective of this project is to explore federated machine learning in TinyML.

S'ofereix una beca d'iniciació a la recerca de 20 hores/setmana amb un salari aprox. de 600 Euros/mes per realitzar el TFM en el marc del projecte GRAPHSEC.

Check offers of other studies and specializations