Search for dissertations about: "unsupervised"

Showing result 1 - 5 of 153 swedish dissertations containing the word unsupervised.

  2. 1. Unsupervised learning of morphology : Survey, model, algorithm and experiments

    Author : Harald Hammarström; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; HUMANIORA; HUMANITIES;

    Abstract : .... READ MORE

  4. 2. Supervised and Unsupervised Deep Learning Models for Flood Detection

    Author : Ritu Yadav; Yifang Ban; Andrea Nascetti; Nicolas Audebert; KTH; []
    Keywords : TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; Floods; Remote Sensing; Sentinel-1 SAR; Segmentation; Change Detection; DEM; Data Fusion; Time Series; Deep Learning; Unsupervised Learning; Contrastive Learning; Self-Attention; Convolutional LSTM; Variational AutoEncoder VAE ; Geoinformatik; Geoinformatics;

    Abstract : Human civilization has an increasingly powerful influence on the earthsystem. Affected by climate change and land-use change, floods are occurringacross the globe and are expected to increase in the coming years. Currentsituations urge more focus on efficient monitoring of floods and detecting impactedareas. READ MORE

  5. 3. Modeling time-series with deep networks

    Author : Martin Längkvist; Amy Loutfi; Lars Karlsson; Tapani Raiko; Örebro universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; multivariate time-series; deep learning; representation learning; unsupervised; Information technology; Informationsteknologi;

    Abstract : .... READ MORE

  6. 4. Aggregation as Unsupervised Learning in Software Engineering and Beyond

    Author : Maria Ulan; Welf Löwe; Neil Ernst; Linnéuniversitetet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; quality assessment; quantitative methods; aggregation; multi-criteria decision making; unsupervised machine learning; Data- och informationsvetenskap; Computer and Information Sciences Computer Science;

    Abstract : Ranking alternatives is fundamental to effective decision making. However, creating an overall ranking is difficult if there are multiple criteria, and no single alternative performs best across all criteria. Software engineering is no exception. READ MORE

  7. 5. Deep learning for news topic identification in limited supervision and unsupervised settings

    Author : Arezoo Hatefi; Frank Drewes; Johanna Björklund; Xuan-Son Vu; Eric Gaussier; Umeå universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Topic Identification; Data Clustering; News Stream Clustering; Semi-Supervised Learning; Unsupervised Learning; Event Topics; News Stories; Multimodal News; Document Classification; Document Clustering; Deep Learning; Deep Clustering; Pre-trained Language Models;

    Abstract : In today's world, following news is crucial for decision-making and staying informed. With the growing volume of daily news, automated processing is essential for timely insights and in aiding individuals and corporations in navigating the complexities of the information society. READ MORE