• 

  Label Propagation in Machine Learning Systems: Providing End-to-End Traceability with Explainable Artificial Intelligence 

  Ingebrigtsen, Marius Johan (Mastergradsoppgave; Master thesis, 2024-05-15)

  Artificial Intelligence (AI) and the underlying Machine Learning (ML) technology is experiencing increased applications in various areas. The training of ML models requires significant amounts of data, and data might contain restrictions regarding their permitted usage. High-performant models are often called black-boxes because of their complex decision-making process. Thus, ML applications threaten ...
• 

  Bootstrapping the Integrity of Sensor Data Labels at the Microcontroller Level Using Physically Unclonable Functions: Addressing Physical Vulnerabilities in the IoT Domain 

  Monsen, Henrik (Mastergradsoppgave; Master thesis, 2024-05-15)

  Modern decision-making processes across industries today increasingly rely on data-driven insights derived from various sources. As smart devices, sensor tech- nology, and the IoT (Internet of Things) evolve, organizations are progressively leveraging these technologies for data-driven decision-making. However, with the introduction of regulations such as the General Data Protection Regulation (GDPR) ...
• 

  Training and Model Parameters to Defend against Tabular Leakage Attacks 

  Balasubramanian, Pragatheeswaran (Mastergradsoppgave; Master thesis, 2024-05-15)

  Federated Learning (FL) is a privacy-preserving approach to train machine learning models on distributed datasets across different organizations. This is particularly beneficial for domains like healthcare and finance, where user data is often sensitive and tabular (e.g., hospital records and financial transactions). However, recent research like Tableak highlighted vulnerabilities that can exploit ...
• 

  Barne- og ungdomspsykiatri i et lavinntektsland (Nepal). Utfordringer, barrierer og muligheter i pasientbehandling og i samarbeid med distriktene. En kvalitativ studie 

  Somby, Silje Máret; Magga, Kristine Wollmann (Master thesis; Mastergradsoppgave, 2022-06-15)

  Denne masteroppgaven tar for seg hvilke erfaringer kliniske psykologer og psykiatere ved det første BUP-senteret i Nepal har hatt med å utvikle barne- og ungdomspsykiatriske tjenester i et av verdens fattigste land. Det ble gjennomført kvalitative, individuelle dybdeintervjuer på engelsk av til sammen åtte informanter: fire psykologer og fire psykiatere fra BUP-poliklinikken på Kanti Children's ...
• 

  Nature Connectedness in Preschool Children 

  Gustavsson, Helenah (Master thesis; Mastergradsoppgave, 2024-05-02)

  This study aimed to assess nature connectedness in preschool children. Spending time in nature is associated with multiple health benefits, in terms of cognitive, social, and emotional well-being. Individuals who are highly connected to nature tend to spend more time in nature. The objectives of this study were threefold: to examine if children in nature preschools differ in their nature connectedness ...

View more