Sökning: "intermediate domain"

Visar resultat 1 - 5 av 20 uppsatser innehållade orden intermediate domain.

  1. 1. Playstyle Generation with Multimodal Generative Adversarial Imitation Learning : Style-reward from Human Demonstration for Playtesting Agents

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

    Författare :William Ahlberg; [2023]
    Nyckelord :Imitation Learning; Reinforcement Learning; Game-testing; Imitationsinlärning; Förstärkande inlärning; Speltestning;

    Sammanfattning : Playtesting plays a crucial role in video game production. The presence of gameplay issues and faulty design choices can be of great detriment to the overall player experience. LÄS MER

  3. 2. Super-Resolution Vehicle Trajectory using Recurrent Time Series Imputation

    Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Hasnain Roopawalla; [2022]
    Nyckelord :;

    Sammanfattning : Vehicle data finds its use in a variety of applications in the fields of machine learning and data analysis. The volume of available data is limited by the frequency of data collection, and for several reasons, it can be infeasible to simply amplify this frequency. LÄS MER

  4. 3. Spectral density approach for dynamic analysis of high-speed railway bridges

    Master-uppsats, KTH/Bro- och stålbyggnad

    Författare :Alket Ciku; Vlad Gavriliuc; [2022]
    Nyckelord :;

    Sammanfattning : The focus of this thesis is to introduce the concept of train signature in the spectraldensity approach used in the dynamic analysis of simply-supported railway bridges.Due to the increased transportation demands, longer trains with higher axles loadsand top speeds are being developed. LÄS MER

  5. 4. Online Unsupervised Domain Adaptation

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

    Författare :Theodoros Panagiotakopoulos; [2022]
    Nyckelord :Unsupervised Domain Adaptation; Continual Learning; Curriculum Learning; Clear2Rain; Self-Supervised Learning; Semantic Segmentation; Transfer Learning; Online Learning; Unsupervised Domain Adaptation; Kontinuerligt lärande; Curriculum Learning; Clear2Rain; Self-Supervised Learning; Semantisk Segmentering; Transfer Learning; Online Learning;

    Sammanfattning : Deep Learning models have seen great application in demanding tasks such as machine translation and autonomous driving. However, building such models has proved challenging, both from a computational perspective and due to the requirement of a plethora of annotated data. LÄS MER

  7. 5. 3D Reconstruction from Satellite Imagery Using Deep Learning

    Master-uppsats, Linköpings universitet/Datorseende

    Författare :Tim Yngesjö; [2021]
    Nyckelord :3D reconstruction; Deep learning;

    Sammanfattning : Learning-based multi-view stereo (MVS) has shown promising results in the domain of general 3D reconstruction. However, no work before this thesis has applied learning-based MVS to urban 3D reconstruction from satellite images. In this thesis, learning-based MVS is used to infer depth maps from satellite images. LÄS MER