Sökning: "Trustworthy AI"

Hittade 5 avhandlingar innehållade orden Trustworthy AI.

  1. 1. Trustworthy explanations : Improved decision support through well-calibrated uncertainty quantification

    Författare :Helena Löfström; Ulf Seigerroth; Ulf Johansson; Patrick Mikalef; Jönköping University; []
    Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Explainable Artificial Intelligence; Interpretable Machine Learning; Decision Support Systems; Uncertainty Estimation; Explanation Methods;

    Sammanfattning : The use of Artificial Intelligence (AI) has transformed fields like disease diagnosis and defence. Utilising sophisticated Machine Learning (ML) models, AI predicts future events based on historical data, introducing complexity that challenges understanding and decision-making. LÄS MER

  3. 2. 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

  4. 3. Intelligent Data and Potential Analysis in the Mechatronic Product Development

    Författare :Alexander Nüssgen; Margot Ruschitzka; Cecilia Boström; Edeltraud Leibrock; Uppsala universitet; []
    Nyckelord :Intelligent Data; Potential Analysis; Mechatronic Product Development; Artificial Intelligence; Decision Support Framework; Knowledge Management; Human Experts; Trustworthy AI; Artificiell intelligens; Artificial Intelligence;

    Sammanfattning : This thesis explores the imperative of intelligent data and potential analysis in the realm of mechatronic product development. The persistent challenges of synchronization and efficiency underscore the need for advanced methodologies. LÄS MER

  5. 4. Neural networks in context: challenges and opportunities : a critical inquiry into prerequisites for user trust in decisions promoted by neural networks

    Författare :Lars Holmberg; Paul Davidsson; Per Linde; Carl Magnus Olsson; Maria Riveiro; Malmö universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Explainable AI; Machine Learning; Neural Network; Concept; Generalisation; Out-of-Distribution; Förklaringsbar AI; Maskininlärning; Neurala Nätverk; Koncept; Generalisering; Utanför-distributionen;

    Sammanfattning : Artificial intelligence and machine learning (ML) in particular increasingly impact human life by creating value from collected data. This assetisation affects all aspectsof human life, from choosing a significant other to recommending a product for us to consume. LÄS MER

  7. 5. Generalisation and reliability of deep learning for digital pathology in a clinical setting

    Författare :Milda Pocevičiūtė; Claes Lundström; Stina Garvin; Gabriel Eilertsen; Nasir Rajpoot; Linköpings universitet; []
    Nyckelord :MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; Deep learning; Digital pathology; Generalisation; Uncertainty estimation; Anomaly detection; Data distribution shift;

    Sammanfattning : Deep learning (DL) is a subfield of artificial intelligence (AI) focused on developing algorithms that learn from data to perform some tasks that can aid humans in their daily life or work assignments. Research demonstrates the potential of DL in supporting pathologists with routine tasks like detecting breast cancer metastases and grading prostate cancer. LÄS MER