Search for dissertations about: "Meta learning"

Showing result 1 - 5 of 60 swedish dissertations containing the words Meta learning.

  2. 1. Sharing to learn and learning to share : Fitting together metalearning and multi-task learning

    Author : Richa Upadhyay; Marcus Liwicki; Ronald Phlypo; Rajkumar Saini; Atsuto Maki; Luleå tekniska universitet; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Multi-task learning; Meta learning; transfer learning; knowledge sharing algorithms; Machine Learning; Maskininlärning;

    Abstract : This thesis focuses on integrating learning paradigms that ‘share to learn,’ i.e., Multitask Learning (MTL), and ‘learn (how) to share,’ i.e. READ MORE

  4. 2. Machine learning for building energy system analysis

    Author : Fan Zhang; Johan Håkansson; Chris Bales; Stefan Byttner; Högskolan Dalarna; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; district heating; machine learning; deep learning; HVAC; neural networks;

    Abstract : Buildings account for approximately 40% of the global energy, and Heating, Ventilation, and Air Conditioning (HVAC) contributes to a large proportion of building energy consumption. Two main negative characteristics that contribute to performance degradation and energy waste in an HVAC system are inappropriate control strategies and faults. READ MORE

  5. 3. Designing for Adaptable Learning

    Author : Amir Haj-Bolouri; Lars Svensson; Thomas Winman; Per Flensburg; Högskolan Väst; []
    Keywords : SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Design; action design research; design science research; information systems; integration work; civic orientation; work-integrated learning; e-learning; adaptable learning; Work Integrated Learning; Arbetsintegrerat lärande; Informatik; Informatics;

    Abstract : The research in this thesis emphasizes the endeavor of designing for adaptable learning. Designing for adaptable learning is understood as an overall response to designing for integration work. Designing for integration work is thus classified as a special case of designing for adaptable learning. READ MORE

  6. 4. Visual Analytics for Explainable and Trustworthy Machine Learning

    Author : Angelos Chatzimparmpas; Andreas Kerren; Rafael M. Martins; Ilir Jusufi; Alex Endert; Linnéuniversitetet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; visualization; interaction; visual analytics; explainable machine learning; XAI; trustworthy machine learning; ensemble learning; dimensionality reduction; supervised learning; unsupervised learning; ML; AI; tabular data; visualisering; interaktion; visuell analys; förklarlig maskininlärning; XAI; pålitlig maskininlärning; ensembleinlärning; dimensionesreducering; övervakad inlärning; oövervakad inlärning; ML; AI; tabelldata; Computer Science; Datavetenskap; Informations- och programvisualisering; Information and software visualization;

    Abstract : The deployment of artificial intelligence solutions and machine learning research has exploded in popularity in recent years, with numerous types of models proposed to interpret and predict patterns and trends in data from diverse disciplines. However, as the complexity of these models grows, it becomes increasingly difficult for users to evaluate and rely on the model results, since their inner workings are mostly hidden in black boxes, which are difficult to trust in critical decision-making scenarios. READ MORE

  7. 5. Virtual Learning Environments in Higher Education : A Study of User Acceptance

    Author : Christina Keller; Sven Carlsson; Birger Rapp; Fredrik Nilsson; Lars Svensson; Linköpings universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; e-learning; web-based learning; virtual learning environment; technology acceptance; organisational learning; diffusion of innovations; Informatics; Informatik; Economic Information Systems; Ekonomiska informationssystem;

    Abstract : The aim of the thesis was to create knowledge about factors influencing acceptance of virtual learning environments among academic staff and students in blended learning environments. The aim was operationalised by four research questions. READ MORE