Search for dissertations about: "data augmentation"

Showing result 1 - 5 of 59 swedish dissertations containing the words data augmentation.

  2. 1. Data-driven AI Techniques for Fashion and Apparel Retailing

    Author : Chandadevi Giri; Ulf Johansson; Jenny Balkow; Xianyi Zeng; Sebastien Thomessey; Maria Riveiro; Högskolan i Borås; []
    Keywords : SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Digitalization; artificial intelligence; fashion and apparel industry; churn prediction; sales forecasting; campaign analysis; data driven AI decision-making; 数字化，人工智能，服装产业，客户流失预测，销售预测，竞争分析，数据驱动的人 工智能决策; Digitalisation; intelligence artificielle IA; industrie de la mode et de l habillement; prédiction de désabonnement; prévision des ventes; analyse des promotions; Prise de décision par IA axée sur les données; Digitalisering; Artificiell intelligens; Modeindustrin; Churnprediktion; Försäljningsprognoser; Kampanjanalys; Datadriven AI; Beslutsstöd; Business and IT; Handel och IT; Textil och mode generell ; Textiles and Fashion General ;

    Abstract : Digitalisation allows companies to develop many new ways of interacting with customers and other stakeholders. These digital interactions typically generate data that can be stored and later processed for different objectives. READ MORE

  4. 2. Improving Language Models Using Augmentation and Multi-Modality

    Author : Tobias Norlund; Chalmers tekniska högskola; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; natural language processing; contextual augmentation; multimodal language modeling; language models;

    Abstract : Language models have become a core component in modern Natural Language Processing (NLP) as they constitute a powerful base that is easily adaptable to many language processing tasks. Part of the strength lies in their ability to embed associations representing general world knowledge. READ MORE

  5. 3. Synthetic data for visual machine learning : A data-centric approach

    Author : Apostolia Tsirikoglou; Jonas Unger; Gabriel Eilertsen; Anders Ynnerman; Philipp Slusallek; Linköpings universitet; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Training data; Synthetic images; Computer graphics; Generative modeling; Natural images; Histopathology; Digital pathology; Machine learning; Deep learning;

    Abstract : Deep learning allows computers to learn from observations, or else training data. Successful application development requires skills in neural network design, adequate computational resources, and a training data distribution that covers the application do-main. READ MORE

  6. 4. Resource efficient automatic segmentation of medical images

    Author : Minh Hoang Vu; Tommy Löfstedt; Tufve Nyholm; Anders Garpebring; Joakim Jonsson; Örjan Smedby; Umeå universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; radiotherapy; medical imaging; deep learning; convolutional neural network; generative adversarial network; data augmentation; semantic segmentation; classification; activation map compression; radiofysik; radiation physics;

    Abstract : Cancer is one of the leading causes of death worldwide. In 2020, there were around 10 million cancer deaths and nearly 20 million new cancer cases in the world. Radiation therapy is essential in cancer treatments because half of the cancer patients receive radiation therapy at some point. READ MORE

  7. 5. Unobtrusive Augmentation  of Physical Environments : Interaction Techniques, Spatial Displays and Ubiquitous Sensing

    Author : Alex Olwal; Steven Feiner; Lennart Johnsson; Yngve Sundblad; Mark Billinghurst; KTH; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Computer science; Datalogi;

    Abstract : The fundamental idea of Augmented Reality (AR) is to improve and enhance our perception of the surroundings, through the use of sensing, computing and display systems that make it possible to augment the physical environment with virtual computer graphics. AR is, however, often associated with user-worn equipment, whose current complexity and lack of comfort limit its applicability in many scenarios. READ MORE