Available Master topics: Machine Learning

Remove unwanted objects in 1-2-3. Algorithms and software for advanced video processing suitable for non-experienced user.
Develop and evaluate data-driven techniques and prototypes for automatically analyzing developer sentiment in commit message or code comments, and investigating if and how developer sentiment impacts software fault-proneness or software maintainability.
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.
Use machine learning and video processing techniques to cut video events in sports videos. E.g., find the best start and stop times for a goal in a soccer video.
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.
Developing a system (or machine learning model) that can generate a face image based on the semantic text information about the face.
Survey the literature, techniques, tools, and tactics employed by competitors in DARPA's Cyber Grand Challenge, and use selected techniques, tools, and tactics to develop and evaluate a prototype autonomous secure and resilient system.
Develop and evaluate data-driven techniques and prototypes for detecting API misuse based on deviations from frequent usage patterns in large corpora of source code.
Develop and evaluate data-driven techniques and prototypes for mining API usage specifications from large corpora of source code.
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.
Deepfake can create realistic AI-generated videos show real people doing and saying fictional things. Can we build a tool to detect such the fake videos?
This project involves developing new methods to design, develop, and test NASA JPL's Open Source Rover, which is a scaled-down version of real Mars Rover used on Mars.
The detection of abnormalities in the gastrointestinal tract can help to reduce the chances of colorectal cancer and provide successful treatment. Towards fulfilling this goal, we target to build a generalizable and robust machine learning that can improve the healthcare system by automatically segmenting and detecting diseases and instruments inside the GI tract.
Cellular and Internet of Things (IoT) massive deployment is increasingly questioning the possibility to handle several network functionalities, such as resource allocation and service dissemination, by using few centralized network entities. The analysis and design of scalable and robust solutions for decentralized network management, characterized by highly-performing learning schemes, is thus needed, aiming to satisfy end-user demands in terms of Quality of Service and Experience (QoS/QoE).
Graph neural networks (GNNs) represent the next step in the evolution of deep learning. We aim to use GNNs as a tool for the detection of fake news.
Explain the prediction of a deep neural network analyzing microscopic videos of human semen.
This topic explores the potential of using synthetic data to train machine learning algorithms in fields that don’t have a lot of open annotated datasets, such as medicine.
NCCL (pronounced "Nickel") is a stand-alone library of standard collective communication routines for GPUs. It has been optimized to achieve high bandwidth on platforms using PCIe, NVLink, NVswitch, as well as networking using TCP/IP sockets. NCCL supports an arbitrary number of GPUs installed in a single node or across multiple nodes and can be used in either single- or multi-process (e.g., MPI) applications.
Data-driven medical systems for disease prevention rely on multimodal data streams for decision making. The representations of each data stream can be ordered in graphs. In this topic, students will explore graph convolutional neural networks for deciding steps within a medical system to prevent life-style diseases developing in its users.
The Internet of Things (IoT) deployment is underway all over the world. This makes possible the experimental analysis of several IoT technologies in real scenarios and use cases, aiming to pinpoint possible issues and moving forward enhancements and optimization.
The project will focus on developing coupled factorization-based approaches that can identify shared and unshared patterns across data sets from multiple sources and using the developed methods in a real metabolomics application.
Compare, benchmark, and optimize machine learning frameworks.
Is this viral image fake or real? Can I trust this news article with soul-catching picture of disaster, hungry child or violence? Have I seen this image before in different context? We need an approach to answer these questions!
Medical data is important to develop AI systems for future health care improvements. Often medical data is hard to obtain due to legal and hospital restrictions. The idea behind the thesis is to tap into the waste data shared on the internet and research if there are sources that can be used to obtain medical data.
Developing a system (or machine learning model) that can try to predict or confirm the emotional mind state of a subject given additional information like pulse rate blood pressure etc.
Message Passing Interface (MPI) is a standardized and portable message-passing system designed by researchers from academia and industry to function on a wide variety of parallel computers.
Sometimes mass-media, news agencies and social networks start to write, post and re-post a huge amount of information about a single event that can be both real and fake. Can we detect this waves at early stage, especially if the initial source was completely fake?
NVMe over Fabrics (NVMe-oF) is an industry-standard for providing fast access to remote storage devices. By relying on remote direct memory access (RDMA), devices can read and write directly to remote memory over a network (“fabric”) with very little overhead. Dolphin’s PCIe technology allows devices to use native DMA to remote memory directly, without relying on an RDMA transport protocol.
Generating segmentation mask of polyps of Gastrointestinal Tract (GI) images collected from endoscopic videos is an important task for analyzing GI tract videos. This segmentation task can be achieved by the state of the art GAN architectures by generating synthetic polyps conditioned on segmentation masks.
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.
The 5th Generation of cellular systems (5G) is about to be on the market. Nowadays, 5G testbeds are being developed all over the world, in order to test 5G in real scenarios and use cases, aiming to pinpoint possible issues and moving forward enhancements and optimization.
The amount of electric cars increasing rapidly, especially in Norway. Problems and questions started to arise and some of them are really important both for electric car owners and the nature. Some of issues, like battery utilization, need to be addressed on system-level. But some are solvable right now using modern data analysis and smart planning.
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.
The thesis will focus on the use of various tensor factorization models (multi-way data analysis) to capture the underlying patterns as well as evolution of those patterns in multi-way data. The primary application of interest will be a neuroscience application.
This research is focused on generating sperm segmentations to predict motility and morphology levels of sperms videos in the Visem open dataset. To accomplish this, the CycleGAN architecture will be used with computer-generated synthetic segmented sperm images.
Use machine learning to generate an avatar that responds to audio and video input from a person and generates an answer delivered by a virtual avatar with corresponding facial expressions.