Essays about: "Tolkningsbarhet"

Showing result 1 - 5 of 19 essays containing the word Tolkningsbarhet.

  1. 1. Explainable modeling in machine learning : A comparative study

    University essay from Umeå universitet/Statistik

    Author : Simon Stålberg; Olivia Isaksson; [2023]
    Keywords : ;

    Abstract : As the use of advanced machine learning models has increased, the need for explainability that these models lack concerning their prediction has increased simultaneously. The aim of this thesis is to compare different functions available in the program R regarding their ability to provide explainability for these advanced machine learning models, also commonly referred to as black-box models. READ MORE

  2. 2. Counterfactual and Causal Analysis for AI-based Modulation and Coding Scheme Selection

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Kun Hao; [2023]
    Keywords : Explainable Artificial Intelligence; Counterfactual; Causal Analysis; Shapley Additive Explanations; Modulation and Coding Scheme; Förklarlig artificiell intelligens; kontrafaktisk analys; orsaksanalys; Shapley tillsatsförklaringar; modulerings och kodningsschema;

    Abstract : Artificial Intelligence (AI) has emerged as a transformative force in wireless communications, driving innovation to address the complex challenges faced by communication systems. In this context, the optimization of limited radio resources plays a crucial role, and one important aspect is the Modulation and Coding Scheme (MCS) selection. READ MORE

  3. 3. Aggregating predictions of a yeast semantic segmentation model : Reducing a pixel classifier into a binary image classifier

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Ali Muquri; [2023]
    Keywords : ;

    Abstract : The introduction of machine learning in clinical microbiology is important for aiding clinical laboratories with highly repetitive tasks that are fatiguing, error-prone, and require long employee training time due to the complex nature of the task. A challenging task that belongs to the subareas that need assistance is yeast detection in fluorescence microscopy where various yeast morphologies exist. READ MORE

  4. 4. Explainability to enhance creativity : A human-centered approach to prompt engineering and task allocation in text-to-image models for design purposes

    University essay from Luleå tekniska universitet/Institutionen för ekonomi, teknik, konst och samhälle

    Author : Celina Burlin; [2023]
    Keywords : ;

    Abstract : As the power, utility, and prevalence of generative AI technologies continue to grow, the debate on whether and how designers should incorporate text-image models into the design process is gaining momentum. To ensure productivity, creativity, and human values, this project seeks to address design interaction and task allocation between designers, and generative AI models become essential. READ MORE

  5. 5. Applying the Shadow Rating Approach: A Practical Review

    University essay from KTH/Matematik (Avd.)

    Author : Viktor Barry; Carl Stenfelt; [2023]
    Keywords : Shadow Rating; probability of default; low default portfolio; credit risk; statistical learning; financial regulation; Basel; Pluto and Tasche; Skuggrating; sannolikhet av fallissemang; lågfallissemangsportfölj; kreditrisk; statistisk inlärning; finansiella regelverk; Basel; Pluto och Tasche;

    Abstract : The combination of regulatory pressure and rare but impactful defaults together comprise the domain of low default portfolios, which is a central and complex topic that lacks clear industry standards. A novel approach that utilizes external data to create a Shadow Rating model has been proposed by Ulrich Erlenmaier. READ MORE