Sökning: "deep learning"

Visar resultat 1 - 5 av 877 uppsatser innehållade orden deep learning.

  1. 1. Interactionwise Semantic Awareness in Visual Relationship Detection

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Pagliarini Giovanni; Imtiaz Azfar; [2020-11-06]
    Nyckelord :Deep Learning; Natural Language Processing; Computer Vision; Visual Relationship Detection; Object Detection;

    Sammanfattning : Visual Relationship Detection (VRD) is a relatively young research area, where thegoal is to develop prediction models for detecting the relationships between objectsdepicted in an image. A relationship is modeled as a subject-predicate-object triplet,where the predicate (e.g an action, a spatial relation, etc. LÄS MER

  3. 2. Geo-temporal Online Analysis of Traffic Rule Violations

    Kandidat-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Adam Davidsson; Dyako Fatih; Simon Larsson; Jesper Naarttijärvi; Daniel Nilsson; Marcus Svensson; [2020-10-30]
    Nyckelord :Traffic rule violations; Risk estimation; Privacy preservation; Computer vision; Deep learning neural net;

    Sammanfattning : Due to inattention and not complying with traffic regulations, human error accounts forroughly 94% of all traffic accidents. To counter this, the need to develop systems that canidentify traffic rule violations and calculate the risk of collisions. The information reportedcan then be used to implement preventive measures. LÄS MER

  4. 3. Deep Learning for Deep Water: Robust classification of ship wakes with expert in the loop

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Igor RYAZANOV; [2020-10-06]
    Nyckelord :machine learning; deep learning; pattern recognition; acoustic data analysis; shipping data; data augmentation; noise robustness; classification with data imbalance; expert-in-the-loop framework;

    Sammanfattning : This work examines the applicability of the deep learning models to pattern recognitionin acoustic ocean data. The features of the dataset include noise, data scarcityand the lack of labeled samples. A deep learning model is proposed for the task ofautomatic wake detection. LÄS MER

  5. 4. Resource Optimal Neural Networks for Safety-critical Real-time Systems

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Joakim Åkerström; [2020-07-10]
    Nyckelord :Data science; machine learning; deep learning; neural networks; network compression; network acceleration; safety-critical systems; real-time systems;

    Sammanfattning : Deep neural networks consume an excessive amount of hardware resources, makingthem difficult to deploy to real-time systems. Previous work in the field of networkcompression lack the explicit hardware feedback necessary to control the resourceconstraints imposed by such systems. LÄS MER

  7. 5. Text analysis for email multi label classification

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Kyriaki Paniskaki; Sanjit Harsha Kadam; [2020-07-08]
    Nyckelord :natural language processing; machine learning; multi label text classification; deep neural networks; bilingual texts; emails; short texts;

    Sammanfattning : This master’s thesis studies a multi label text classification task on a small dataset of bilingual, English and Swedish, short texts (emails). Specifically, the size ofthe data set is 5800 emails and those emails are distributed among 107 classes withthe special case that the majority of the emails includes the two languages at thesame time. LÄS MER