Sökning: "Feature Attribution"

Visar resultat 1 - 5 av 11 uppsatser innehållade orden Feature Attribution.

  1. 1. Enhancement of a Power Line Information System by Combining BIM and LiDAR Data

    Master-uppsats, KTH/Lantmäteri – fastighetsvetenskap och geodesi

    Författare :Daniel Wollberg; [2024]
    Nyckelord :GIS; BIM; FME; CloudCompare; GIS; BIM; FME; CloudCompare;

    Sammanfattning : With the great ongoing energy transition in Sweden, Svenska Kraftnät (SVK) sees a huge need for investment in the Swedish transmission network and supporting IT- systems.  SVK has a great amount of collected laser data over the electric power transmission network however this data does not contain any semantic attribution that can be analyzed on broader information systems. LÄS MER

  3. 2. PVCFA: Principal Variation Context Feature Attribution : Distributed Chess for Perturbation-based Saliency Maps

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

    Författare :Marco Molinari; [2023]
    Nyckelord :Chess; Perturbation; Saliency maps; Multiagent; Reinforcement Learning; Schack; Perturbation; Saliency maps; Multiagent; Reinforcement Learning;

    Sammanfattning : The research and development field of computer chess improved more in the last 5 years than in the whole history of computers. Unfortunately these unprecedented results comes with techniques that don’t leave much space to intuition and comprehensibility for humans. LÄS MER

  4. 3. Evaluating Marketing Initiatives using Explainable Machine Learning : An Alternative to Attribution Models

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

    Författare :João Ferreira; [2023]
    Nyckelord :Explainable Machine Learning; Attribution models; Marketing Automation; Search Engine Optimization; A B testing; Definierad maskininlärning; Attributionsmodeller; Automatisering av marknadsföring; Optimering av sökmotor; A B-tester;

    Sammanfattning : Since its inception, Marketing has always needed more clearly defined incrementality, i.e., a measurement of advertisement effectiveness. Nowadays, Marketing is an evergrowing business; within it, Digital Marketing is taking the spotlight. LÄS MER

  5. 4. 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

  7. 5. Stylometric Embeddings for Book Similarities

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

    Författare :Beichen Chen; [2021]
    Nyckelord :Stylometry; Authorship attribution; Embeddings; Neural networks; Natural language processing; Book recommendations; Stilometri; Författarbestämning; Vektorrum; Neurala nätverk; Språkteknologi; Bokrekommendationer;

    Sammanfattning : Stylometry is the field of research aimed at defining features for quantifying writing style, and the most studied question in stylometry has been authorship attribution, where given a set of texts with known authorship, we are asked to determine the author of a new unseen document. In this study a number of lexical and syntactic stylometric feature sets were extracted for two datasets, a smaller one containing 27 books from 25 authors, and a larger one containing 11,063 books from 316 authors. LÄS MER