Avancerad sökning

Hittade 2 uppsatser som matchar ovanstående sökkriterier.

1. 1. 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

3. 2. Assessing the impact of floating-point precision in plasma simulations : A study of precision reduction and precisionrefinement in iPIC3D

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

   Författare :Svante Sörberg; Simon Tran Florén; [2019]
   Nyckelord :;

   Sammanfattning : This thesis explores how the precision of floating-point numbers affects the high-performance, implicit particle-in-cell plasma simulation software iPIC3D. We investigate whether a version of iPIC3D, modified to use floatingpoint numbers in lower precision than the current 64 bit double-precision, could yield accurate simulations in comparison with the current version. LÄS MER