Sökning: "Representation Learning"

Visar resultat 6 - 10 av 246 avhandlingar innehållade orden Representation Learning.

  1. 6. Gender and representation : investigations of bias in natural language processing

    Författare :Hannah Devinney; Henrik Björklund; Jenny Björklund; Christian Hardmeier; Umeå universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; NLP; natural language processing; gender bias; social impact of AI; gendered pronouns; neopronouns; gender studies; topic modeling; Computer Science; datalogi; computational linguistics; datorlingvistik; genusvetenskap; gender studies;

    Sammanfattning : Natural Language Processing (NLP) technologies are a part of our every day realities. They come in forms we can easily see as ‘language technologies’ (auto-correct, translation services, search results) as well as those that fly under our radar (social media algorithms, 'suggested reading' recommendations on news sites, spam filters). LÄS MER

  3. 7. 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

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

    Författare :Angelos Chatzimparmpas; Andreas Kerren; Rafael M. Martins; Ilir Jusufi; Alex Endert; Linnéuniversitetet; []
    Nyckelord :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;

    Sammanfattning : 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. LÄS MER

  5. 9. Learning and Evaluating the Geometric Structure of Representation Spaces

    Författare :Petra Poklukar; Danica Kragic; Søren Hauberg; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Representation Learning; Machine Learning; Generative Models; Computer Science; Datalogi;

    Sammanfattning : Efficient representations of observed input data have been shown to significantly accelerate the performance of subsequent learning tasks in numerous domains. To obtain such representations automatically, we need to design both i) models that identify useful patterns in the input data and encode them into structured low dimensional representations, and ii) evaluation measures that accurately assess the quality of the resulting representations. LÄS MER

  7. 10. 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