Available Master topics: Machine Learning

Manually tagging and processing video is time consuming. Here, we want to automate the task of generating events and summaries, like the clips shown in the sport news, using for example machine learning.
Memory training exercises are known to have a positive effect on improving the memorability of humans. A memory training task can be as simple as trying to remember a password of increasing complexity or a number of varying length.
Interested in sports? Technology used by real athletes? Analysing wellness and training load data is important to avoid injuries and increase performance. Here, the aim is to build a system to automatically analyse and predict outcomes ...
This topic focuses on developing automated testing methods for cancer registration and support system at Cancer Registry of Norway.
Developing automated testing tools for telehealth services at Oslo City.
Use machine learning and video processing techniques to automatically find events in sports videos. For example, in football, some "easy" ones are goals, but others like tackles are harder.
Develop and evaluate data-driven techniques and prototypes for automatically repairing security vulnerabilities in source code.
Investigate, develop and evaluate data-driven techniques and prototypes that help software engineers build software systems that are autonomously self-healing. These are systems that can understand when they are not operating correctly and, without human intervention, make the necessary adjustments to restore themselves to normal operation.
This project focuses on building digital twins for Smart Buildings (e.g., Smart Hospitals) and Smart Power Generators (e.g., Wind Turbines) for advanced analyses with AI techniques.
How can we divide massive data streams meaningful classes without accessing the full dataset ? In this thesis we will explore clustering algorithms that can deal with data as it is scraped from social networks.
Develop and evaluate data-driven techniques and prototypes for automatically assessing the security of a software system by analyzing the system's source code for potential security vulnerabilities during the development stage.
This project involves developing new methods to design, develop, and test Autonomous Rovers, similar to those used on Mars.
Over the recent years Generative Adversarial Models (GANs) have revolutionized the field of artificial intelligence (AI). Given a set of training data, the models can generate outcomes with striking similarities in properties to the training data. E.g. if the training data is a set of images, the models are able to generate new images with the same properties and look stunningly realistic. However the theoretical foundation of GANs is still immature and further understanding is needed. For example, GANs have been criticised to possibly only replicate a limited set of the properties in the training data.
This topic is about developing digital twins for various types of cyber-physical systems.
Explain the prediction of a deep neural network analyzing microscopic videos of human semen.
Survey experiments in studies of political and electoral behavior using profiles of potential candidates are standard practice in political science. With this type of experiments, the researchers' goal is to test which characteristics voters value most in political candidates. One of the main challenges, however, is to generate realistic profiles to be tested. One of the important components of these profiles are the faces of candidates. A potential option is to use faces of real candidates, but this involves complex legal and ethical issues. Another option is to hire models to represent candidates, but this can be expensive and time-consuming.
How can we predict traffic in connected systems such as road networks, and how can we use these predictions to place charging stations for electrical vehicles ? Graph neural networks are currently the most promising approach for studying these question.
In this thesis, the research question is whether regular close-range images with low-cost sensors (tablet camera) of certain field sections are suitable for growth modeling of soybean. Specifically, the effects of different land use intensities on soybean growth patterns shall be investigated using current methods of image analysis and plant phenotyping. Within the scope of the work, a comprehensive image data set along growth period will be generated. The development of a suitable experimental setup for stable and repeatable image acquisition at constant height and perspective with suitable georeferencing, as well as the execution of the photo campaign are essential parts of this work.
In this thesis, the research question is whether regular close-range images with low-cost sensors (tablet camera) of certain field sections are suitable for growth modeling of soybean. Specifically, the effects of different land use intensities on soybean growth patterns shall be investigated using current methods of image analysis and plant phenotyping. Within the scope of the work, a comprehensive image data set along growth period will be generated. The development of a suitable experimental setup for stable and repeatable image acquisition at constant height and perspective with suitable georeferencing, as well as the execution of the photo campaign are essential parts of this work.
We collected large amounts of data from the online social network Twitter and reconstructed the underlying interaction network. This thesis aims to develop and implement a for information diffusion, which we plan to apply on misinformation and conspiracy data.
Construction, evaluation and reasoning using knowledge graphs for software vulnerability assessments.
In this project we will explore techniques to estimate the parameters of a model, when the likelihood or loss function cannot be computed. A popular framework is approximate Bayesian computing (ABC), and we will explore new estimation methods within this framework.
The goal is to apply existing quantum search algorithms or develop new quantum search and optimization algorithms to solve classical optimization problems.
Quantiles are fundamental in statistics and machine learning. In this project we will explore new algorithms that are able to estimate quantiles in real-time.
Automatic classification of sport news into different categories using state of the art Natural Language Processing (NLP). The project is building upon an existing dataset of Norwegian soccer news.
Time series analysis using Residual neural networks. The main task is to explore how different ResNets can be combined to solve complex time series problems.
Developing methods based on AI techniques to discover unforeseen situations in Elevators.
We will explore generative adversarial network models(GANs) to capture spatial dependencies in forecasting uncertainty, e.g. when predicting the next frame in a video or the weather tomorrow.