Sökning: "Multiclass"

Visar resultat 1 - 5 av 17 uppsatser innehållade ordet Multiclass.

  1. 1. Language Classification of Music Using Metadata

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för systemteknik

    Författare :Linus Roxbergh; [2019]
    Nyckelord :Music; Metadata; Language; Classification; Machine Learning; Spotify; Multiclass; Feature Importance;

    Sammanfattning : The purpose of this study was to investigate how metadata from Spotify could be used to identify the language of songs in a dataset containing nine languages. Features based on song name, album name, genre, regional popularity and vectors describing songs, playlists and users were analysed individually and in combination with each other in different classifiers. LÄS MER

  2. 2. APPLICATIONS OF DEEP LEARNING IN TEXT CLASSIFICATION FOR HIGHLY MULTICLASS DATA

    Master-uppsats, Uppsala universitet/Statistiska institutionen

    Författare :Adam Grünwald; [2019]
    Nyckelord :ULMFiT; Neural Networks; NLP; LSTM; Transfer Learning;

    Sammanfattning : Text classification using deep learning is rarely applied to tasks with more than ten target classes. This thesis investigates if deep learning can be successfully applied to a task with over 1000 target classes. A pretrained Long Short-Term Memory language model is fine-tuned and used as a base for the classifier. LÄS MER

  3. 3. User Equipment Characterization using Machine Learning

    Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknik

    Författare :Vanessa Fakhoury; Xin Zhou; [2019]
    Nyckelord :machine learning; characterization; massive MIMO; beamforming; neural networks; support vector machine; logistic regression; multiclass neural networks; Technology and Engineering;

    Sammanfattning : With the ever increasing demand for higher data rates and reliability, efficient management of cellular networks remains a challenge. Among other technologies, fifth generation systems are expected to tackle this challenge using large electronically controllable antenna arrays operating in the time division duplex mode. LÄS MER

  4. 4. Gaussian Process Multiclass Classification : Evaluation of Binarization Techniques and Likelihood Functions

    Kandidat-uppsats, Linnéuniversitetet/Institutionen för matematik (MA)

    Författare :Benjamin Ringdahl; [2019]
    Nyckelord :Machine learning; Gaussian process classification; Laplace s approximation; Likelihood functions; Binarization techniques; Class imbalance;

    Sammanfattning : In binary Gaussian process classification the prior class membership probabilities are obtained by transforming a Gaussian process to the unit interval, typically either with the logistic likelihood function or the cumulative Gaussian likelihood function. Multiclass classification problems can be handled by any binary classifier by means of so-called binarization techniques, which reduces the multiclass problem into a number of binary problems. LÄS MER

  5. 5. Contact-free Cognitive Load Classification based on Psycho-Physiological Parameters

    Kandidat-uppsats, Mälardalens högskola/Akademin för innovation, design och teknik; Mälardalens högskola/Akademin för innovation, design och teknik

    Författare :Rikard Gestlöf; Johannes Sörman; [2019]
    Nyckelord :AI; Cognitve Load; Machine Learning;

    Sammanfattning : Cognitive load (CL) is a concept that describes the relationship between the cognitive demands from a task and the environment the task is taking place in, which influences the user’s cognitive resources. High cognitive load leads to higher chance of a mistake while a user is performing a task. LÄS MER