Avancerad sökning

Visar resultat 6 - 10 av 110 avhandlingar som matchar ovanstående sökkriterier.

1. 6. Deep learning for news topic identification in limited supervision and unsupervised settings

   Författare :Arezoo Hatefi; Frank Drewes; Johanna Björklund; Xuan-Son Vu; Eric Gaussier; Umeå universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Topic Identification; Data Clustering; News Stream Clustering; Semi-Supervised Learning; Unsupervised Learning; Event Topics; News Stories; Multimodal News; Document Classification; Document Clustering; Deep Learning; Deep Clustering; Pre-trained Language Models;

   Sammanfattning : In today's world, following news is crucial for decision-making and staying informed. With the growing volume of daily news, automated processing is essential for timely insights and in aiding individuals and corporations in navigating the complexities of the information society. LÄS MER

3. 7. Wicked Problems in Engineering Education : Preparing Future Engineers to Work for Sustainability

   Författare :Johanna Lönngren; Magdalena Svanström; Åke Ingerman; Tom Adawi; John Holmberg; Marie Paretti; Chalmers tekniska högskola; []
   Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; wicked problem; engineering education; sustainability; phenomenography; assessment; rubric; design-based research; action research; perspective shift; ill-structured problems; problem-solving; didactics of natural science; naturvetenskapens didaktik;

   Sammanfattning : Most engineering education today does not adequately prepare students to contribute to sustainability. For example, engineering students often do not learn how to address complex and ill-structured sustainability problems that involve different stakeholders, value conflicts,and uncertainty; such problems are also called wicked problems. LÄS MER

4. 8. Contributions to deep learning for imaging in radiotherapy

   Författare :Attila Simkó; Joakim Jonsson; Tommy Löfstedt; Anders Garpebring; Tufve Nyholm; Veronika Cheplygina; Umeå universitet; []
   Nyckelord :MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; deep learning; medical imaging; radiotherapy; artefact correction; bias field correction; contrast transfer; synthetic CT; reproducibility;

   Sammanfattning : Purpose: The increasing importance of medical imaging in cancer treatment, combined with the growing popularity of deep learning gave relevance to the presented contributions to deep learning solutions with applications in medical imaging.Relevance: The projects aim to improve the efficiency of MRI for automated tasks related to radiotherapy, building on recent advancements in the field of deep learning. LÄS MER

5. 9. Data-Efficient Learning of Semantic Segmentation

   Författare :David Nilsson; Mathematical Imaging Group; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; semantic segmentation; embodied learning; active learning; semantic video segmentation; computer vision; deep learning;

   Sammanfattning : Semantic segmentation is a fundamental problem in visual perception with a wide range of applications ranging from robotics to autonomous vehicles, and recent approaches based on deep learning have achieved excellent performance. However, to train such systems there is in general a need for very large datasets of annotated images. LÄS MER

7. 10. Do excellent engineers approach their studies strategically? : A quantitative study of students' approaches to learning in computer science education

   Författare :Maria Svedin; Olle Bälter; Stefan Hrastinski; Martha Cleveland-Innes; Johan Thorbiörnson; Arnold Pears; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Approaches to learning; computer science engineering education; Computing education research; online learning; Human-computer Interaction; Människa-datorinteraktion;

   Sammanfattning : This thesis is about students’ approaches to learning (SAL) in computer science education. Since the initial development of SAL instruments and inventories in the 70’s, they have been used as a means to understand students’ approaches to learning better, as well as to measure and predict academic achievement (such as retention, grades and credits taken) and other correlating factors. LÄS MER