Essays about: "Feature Attribution"

Showing result 1 - 5 of 7 essays containing the words Feature Attribution.

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

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

    Author : Marco Molinari; [2023]
    Keywords : Chess; Perturbation; Saliency maps; Multiagent; Reinforcement Learning; Schack; Perturbation; Saliency maps; Multiagent; Reinforcement Learning;

    Abstract : 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. READ MORE

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

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

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

    Abstract : 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. READ MORE

  4. 3. Stylometric Embeddings for Book Similarities

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

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

    Abstract : 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. READ MORE

  5. 4. Authorship classification using the Vector Space Model and kernel methods

    University essay from Uppsala universitet/Statistiska institutionen

    Author : Emil Westin; [2020]
    Keywords : vector space model; semantic kernel; support vector machine; bag-of-words;

    Abstract : Authorship identification is the field of classifying a given text by its author based on the assumption that authors exhibit unique writing styles. This thesis investigates the semantic shortcomings of the vector space model by constructing a semantic kernel created from WordNet which is evaluated on the problem of authorship attribution. READ MORE

  6. 5. Text to features for Swedish text

    University essay from Uppsala universitet/Institutionen för informationsteknologi

    Author : Man Dan Ly; [2019]
    Keywords : ;

    Abstract : In text mining, texts are usually transformed into numerical vectors or feature vectors, before they are given to a machine learning algorithm for text classification. In this project, a set of features for classifying tweets in Swedish was created. READ MORE