Advanced search

Showing result 1 - 5 of 33 swedish dissertations matching the above criteria.

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

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

    Abstract : 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. READ MORE

  2. 2. Vacuum Ultraviolet Scanning Photoelectron Microscopy, Instrumentation & Applications

    Author : Ulf Johansson; Lunds universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Photoelectron Microscopy; Spectromicroscopy; Photoemission; Silicon; Oxide desorption; High-Tc superconductor; Physics; Ellipsoidal mirror; Fysik; Chemistry; Kemi; Fysicumarkivet A:1997:Johansson;

    Abstract : This thesis describes the design and characterisation of a vacuum ultraviolet scanning photoelectron microscope as well as results from studies of laterally inhomogeneous surfaces. The instrument utilises synchrotron radiation from an undulator at the 550 MeV storage ring at the MAX-laboratory. READ MORE

  3. 3. Obtaining Accurate and Comprehensible Data Mining Models : An Evolutionary Approach

    Author : Ulf Johansson; Lars Niklasson; Tom Ziemke; Thorsteinn Rögnvaldsson; Linköpings universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Rule extraction; Ensembles; Data mining; Genetic programming; Artificial neural networks; Computer science; Datalogi;

    Abstract : When performing predictive data mining, the use of ensembles is claimed to virtually guarantee increased accuracy compared to the use of single models. Unfortunately, the problem of how to maximize ensemble accuracy is far from solved. READ MORE

  4. 4. Rule extraction - the key to accurate and comprehensible data mining models

    Author : Ulf Johansson; Linköpings universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Computer science; Datavetenskap;

    Abstract : The primary goal of predictive modeling is to achieve high accuracy when the model is applied to novel data. For certain problems this requires the use of complex techniques, such as neural networks, resulting in opaque models that are hard or impossible to interpret. READ MORE

  5. 5. Clades in the "higher land bird assemblage"

    Author : Ulf. S. Johansson; Scott V. Eswards; Stockholms universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Birds; Fåglar; Systematic Zoology; zoologisk systematik och evolutionsforskning;

    Abstract : This thesis summarizes the results of several phylogenetic studies of birds included in the “higher land bird assemblage” (Anomalogonatae sensu Beddard 1898). The phylogenetic analyses are primarily based on gene sequences obtained from the nuclear genome (exons of the c-myc and RAG-1 genes and an intron of the myoglobin gene). READ MORE