Search for dissertations about: "representation learning"
Showing result 1 - 5 of 224 swedish dissertations containing the words representation learning.
-
1. Modularization of the Learning Architecture : Supporting Learning Theories by Learning Technologies
Abstract : This thesis explores the role of modularity for achieving a better adaptation of learning technology to pedagogical requirements. In order to examine the interrelations that occur between pedagogy and computer science, a theoretical framework rooted in both fields is applied. READ MORE
-
2. Representation learning for natural language
Abstract : Artificial neural networks have obtained astonishing results in a diverse number of tasks. One of the reasons for the success is their ability to learn the whole task at once (endto-end learning), including the representations for data. READ MORE
-
3. Representation Learning and Information Fusion : Applications in Biomedical Image Processing
Abstract : In recent years Machine Learning and in particular Deep Learning have excelled in object recognition and classification tasks in computer vision. As these methods extract features from the data itself by learning features that are relevant for a particular task, a key aspect of this remarkable success is the amount of data on which these methods train. READ MORE
-
4. Plug & Play? Stakeholders’ co-meaningmaking of gamification implementations in workplace learning environments
Abstract : This dissertation discusses the implementation process of gamification in organisations’ workplace learning environments, focusing on four stakeholder groups: Administrators, Leaders, Providers and Users. These stakeholder groups are represented across the dissertation’s five articles, which present the results of my investigation of the groups’ meaning attributions to the gamification implementations in their organisations’ learning environments. READ MORE
-
5. Self-supervised Representation Learning for Visual Domains Beyond Natural Scenes
Abstract : This thesis investigates the possibility of efficiently adapting self-supervised representation learning on visual domains beyond natural scenes, e.g., medical imagining and non-RGB sensory images. READ MORE