Sökning: "Förklaringsbar Artificiell Intelligens"

Hittade 2 uppsatser innehållade orden Förklaringsbar Artificiell Intelligens.

1. 1. Explainable Machine Learning for Lead Time Prediction : A Case Study on Explainability Methods and Benefits in the Pharmaceutical Industry

   Master-uppsats, KTH/Hållbar produktionsutveckling (ML)

   Författare :Paul Fussenegger; Niklas Lange; [2022]
   Nyckelord :Lead time; machine learning; explainability; regression analysis; production planning and control; Ledtid; maskininlärning; förklarbarhet; regressionsanalys; produktionsplanering och produktionsstyrning;

   Sammanfattning : Artificial Intelligence (AI) has proven to be highly suitable for a wide range of problems in manufacturing environments, including the prediction of lead times. Most of these solutions are based on ”black-box” algorithms, which hinder practitioners to understand the prediction process. LÄS MER

3. 2. Exploring attribution methods explaining atrial fibrillation predictions from sinus ECGs : Attributions in Scale, Time and Frequency

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Svante Sörberg; [2021]
   Nyckelord :Explainable Artificial Intelligence XAI ; Explainability; Paroxysmal Atrial Fibrillation; Feature Attribution; Förklaringsbar Artificiell Intelligens; Förklarbarhet; Paroxysmalt Förmaksflimmer; Särdragsattribution;

   Sammanfattning : Deep Learning models are ubiquitous in machine learning. They offer state-of- the-art performance on tasks ranging from natural language processing to image classification. The drawback of these complex models is their black box nature. It is difficult for the end-user to understand how a model arrives at its prediction from the input. LÄS MER