Sökning: "Multitask Learning"

Visar resultat 1 - 5 av 9 uppsatser innehållade orden Multitask Learning.

  1. 1. Teaching with Audiobooks in an EFL Classroom : The Didactical Benefits of Envisionment, Inclusion, and Narration in Audiobooks

    Uppsats för yrkesexamina på grundnivå, Högskolan i Halmstad/Akademin för lärande, humaniora och samhälle

    Författare :Cynthia Castillo Silva; Esin Alatas; [2023]
    Nyckelord :Audiobooks; The Graveyard Book; EFL students; Printed book;

    Sammanfattning : This paper aims to investigate how audiobooks can be used didactically in the EFL classroom. The research questions are: “How do EFL students perceive and visualize the storyworld when listening to audiobooks?”, “Does EFL students’ comprehension differ when listening to an audiobook as opposed to reading a printed book”, and lastly, “What are the benefits of using audiobooks didactically in an EFL classroom?”. LÄS MER

  3. 2. Multi-Scale Task Dynamics in Transfer and Multi-Task Learning : Towards Efficient Perception for Autonomous Driving

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

    Författare :Simon Ekman von Huth; [2023]
    Nyckelord :Autonomous Driving; Computer Vision; Deep Learning; Machine Learning; Multi-Task Learning; Transfer Learning; Task Relationships; Task Dynamics; Python; Multi-Scale Representation Learning; Fuss-Free Network; Självkörande Fordon; Datorseende; Djupinlärning; Maskininlärning; Multiuppgiftsinlärning; Överföringsinlärning; Uppgiftsrelationer; Uppgiftsdynamik; Python; Flerskalig Representationsinlärning; Fuss-Free Nätverk;

    Sammanfattning : Autonomous driving technology has the potential to revolutionize the way we think about transportation and its impact on society. Perceiving the environment is a key aspect of autonomous driving, which involves multiple computer vision tasks. LÄS MER

  4. 3. Metadata assisted finetuning with largepre-trained language models forabstractive text summarization : Multi-task finetuning with abstractive text summarization and categoryclassification

    Master-uppsats, Umeå universitet/Institutionen för datavetenskap

    Författare :Max Sjöblom; [2023]
    Nyckelord :;

    Sammanfattning : Text summarization is time-consuming for humans to complete but is still required in many areas. Recent progress in machine learning research, especially in the natural language domain, has produced promising results. LÄS MER

  5. 4. Energy Consumptions for Vehicles using Multitask Learning

    Master-uppsats, Högskolan i Halmstad/Akademin för informationsteknologi

    Författare :Venkata Sai Vivek Uddagiri; Shankara Narayanan Bangalore Ramalingam; [2022]
    Nyckelord :;

    Sammanfattning : This thesis aims to predict energy (fossil fuel and electric) consumption of internal combustion and hybrid vehicles. This thesis is in association with Wireless cars. Accurate prediction of energy consumption in vehicles is vital, as it can pave the way for a more sustainable future. LÄS MER

  7. 5. Reducing Unintended bias in Text Classification using Multitask learning.

    Magister-uppsats, Blekinge Tekniska Högskola

    Författare :Venkata Sai Sukesh Settipalli; Naga Manendra Kumar Dasireddy; [2021]
    Nyckelord :;

    Sammanfattning : .... LÄS MER