Sökning: "Generative modeling"

Visar resultat 1 - 5 av 24 avhandlingar innehållade orden Generative modeling.

  1. 1. Exploring and modeling response process data from PISA : inferences related to motivation and problem-solving

    Författare :Erik Lundgren; Hanna Eklöf; Inga Laukaityte; Per-Erik Lyrén; Samuel Greiff; Umeå universitet; []
    Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; response processes; large-scale assessments; motivation; problem-solving; computational modeling; Bayesian modeling; didactics of educational measurement; beteendevetenskapliga mätningar;

    Sammanfattning : This thesis explores and models response process data from large-scale assessments, focusing on test-taking motivation, problem-solving strategies, and questionnaire response validity. It consists of four studies, all using data from PISA (Programme for International Student Assessment) data. LÄS MER

  3. 2. Unsupervised Learning of Biomolecular Dynamics with Multi-Modal Data

    Författare :Christopher Kolloff; Chalmers tekniska högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; biomolecular dynamics; data-driven modeling; integrative structural biology; generative modeling; multi- modal machine learning; statistical mechanics; augmented Markov models;

    Sammanfattning : The functioning of cells critically depends on the dynamics of biomolecular systems, such as proteins or nucleic acids. Biophysical experiments as well as Molecular Dynamics (MD) simulations are the primary techniques to model and understand the kinetics and thermodynamics of biomolecules. LÄS MER

  4. 3. A Modeling Language for the Description and Development of Tool Chains for Embedded Systems

    Författare :Matthias Biehl; Törngren Martin; Hans Vangheluwe; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Tool Chain; Tool Integration; Domain-Specific Modeling Language; Generative Approach; Lifecycle Support for Embedded System Development;

    Sammanfattning : The development of embedded systems is typically supported by a number of diverse development tools. To achieve seamless tool support throughout the embedded systems development process, tool chains are constructed as software solutions that integrate the development tools. LÄS MER

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

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

    Sammanfattning : 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. LÄS MER

  7. 5. Data-Efficient Representation Learning for Grasping and Manipulation

    Författare :Ahmet Ercan Tekden; Chalmers tekniska högskola; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; Learning from Demonstration; Generative Modeling; Neural Fields; Robot Learning; Data-efficient Representation Learning; Grasping; Robot Manipulation;

    Sammanfattning : General-purpose robotics require adaptability to environmental variations and, therefore, need effective representations for programming them. A common way to acquire such representations is through machine learning. Machine learning has shown great potential in computer vision, natural language processing, reinforcement learning, and robotics. LÄS MER