Sökning: "Knowledge Distillation"

Visar resultat 1 - 5 av 6 avhandlingar innehållade orden Knowledge Distillation.

  1. 1. Enabling Enterprise Live Video Streaming with Reinforcement Learning and Graph Neural Networks

    Författare :Stefanos Antaris; Sarunas Girdzijauskas; Dimitrios Katsaros; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Graph Neural Networks; Reinforcement Learning; Meta-Learning; Knowledge Distillation; Enterprise Liveo Video Streaming;

    Sammanfattning : Over the last decade, video has vastly become the most popular way the world consumes content. Due to the increased popularity, video has been a strategic tool for enterprises. LÄS MER

  3. 2. Snake Gourds, Parasites and Mother Roasting : Medicinal plants, plant repellents, and Trichosanthes (Cucurbitaceae) in Lao PDR

    Författare :Hugo J. de Boer; Lars Björk; Mats Thulin; Thomas Jaenson; Victoria Reyes-Garcia; Uppsala universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Trichosanthes; Ethnobotany; Similarity of Knowledge; Biogeography; Molecular Dating; Brou; Saek; Kry; Mother roasting; Postpartum healthcare; Parturition; Childbirth; Traditional Medicine; Plant repellents; Fermented fish; Biologi med inriktning mot systematik; Biology with specialization in Systematics;

    Sammanfattning : Background. Traditional plant use was studied in Lao PDR. Research focused on medicinal plant use by the Brou, Saek and Kry ethnic groups, traditional plant repellents against parasitic arthropods and leeches, and the phylogeny and biogeography of the medicinally-important snake gourd genus (Trichosanthes, Cucurbitaceae).  Methods. LÄS MER

  4. 3. Self-supervised Representation Learning for Visual Domains Beyond Natural Scenes

    Författare :Prakash Chandra Chhipa; Marcus Liwicki; Seiichi Uchida; Rajkumar Saini; Josep Lladós; Luleå tekniska universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; self-supervised learning; representation learning; computer vision; learning with few labels; Maskininlärning; Machine Learning;

    Sammanfattning : 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. LÄS MER

  5. 4. Machine learning for anomaly detection in edge clouds

    Författare :Javad Forough; Erik Elmroth; Monowar H. Bhuyan; Shahid Raza; Umeå universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Edge Clouds; Anomaly Detection; Machine Learning;

    Sammanfattning : Edge clouds have emerged as an essential architecture, revolutionizing data processing and analysis by bringing computational capabilities closer to data sources and end-users at the edge of the network. Anomaly detection is crucial in these settings to maintain the reliability and security of edge-based systems and applications despite limited computational resources. LÄS MER

  7. 5. Bondeopposition och bondeinflytande under frihetstiden : centralmakten och östgötaböndernas reaktioner i näringspolitiska frågor

    Författare :Kalle Bäck; Stockholms universitet; []
    Nyckelord :HUMANIORA; HUMANITIES;

    Sammanfattning : The main purpose of this thesis is to elucidate what degree the peasants at the local level were able to influence decision making on different levels of society. The study takes its point of departure in the petitions and solicitations of the peasants addressed to district courts (häradsrätter), county governors (landshövdingar) and the Riksdag. LÄS MER