Sökning: "vector quantization"

Visar resultat 1 - 5 av 19 uppsatser innehållade orden vector quantization.

  1. 1. Enhancing Long-Term Human Motion Forecasting using Quantization-based Modelling. : Integrating Attention and Correlation for 3D Motion Prediction

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

    Författare :Luis González Gudiño; [2023]
    Nyckelord :Human Motion Forecasting; Long-Term Prediction; VQ-VAE; Quantization; 3D Human Motion; CMU MoCap Dataset; Transformer; Mänsklig Rörelseprognos; Långsiktig Prognos; VQ-VAE; Kvantisering; 3D-mänsklig rörelse; CMU MoCap Dataset; Transformer;

    Sammanfattning : This thesis focuses on addressing the limitations of existing human motion prediction models by extending the prediction horizon to very long-term forecasts. The objective is to develop a model that achieves one of the best stable prediction horizons in the field, providing accurate predictions without significant error increase over time. LÄS MER

  3. 2. Adaptive Energy Management Strategies for Series Hybrid Electric Wheel Loaders

    Master-uppsats, Linköpings universitet/Fordonssystem

    Författare :Carolina Pahkasalo; André Sollander; [2020]
    Nyckelord :A-ECMS; ECMS; Equivalent Consumption Minimization Strategy; Dynamic Programming; Hybrid Electric Wheel Loader; Pattern Recognition; Machine Learning; Neural Networks; Learning Vector Quantization; Optimal Control;

    Sammanfattning : An emerging technology is the hybridization of wheel loaders. Since wheel loaders commonly operate in repetitive cycles it should be possible to use this information to develop an efficient energy management strategy that decreases fuel consumption. LÄS MER

  4. 3. Unsupervised Audio Spectrogram Compression using Vector Quantized Autoencoders

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

    Författare :Amund Hansen Vedal; [2019]
    Nyckelord :;

    Sammanfattning : Despite the recent successes of neural networks in a variety of domains, musical audio modeling is still considered a hard task, with features typically spanning tens of thousands of dimensions in input space. By formulating audio data compression as an unsupervised learning task, this project investigates the applicability of vector quantized neural network autoencoders for compressing spectrograms – image-like representations of audio. LÄS MER

  5. 4. Electromagnetic Duality in SO(3) Yang-Mills Theory : Bachelor Thesis

    Kandidat-uppsats, Uppsala universitet/Teoretisk fysik

    Författare :Jim Lundin; [2018]
    Nyckelord :Montonen-Olive conjecture; BPS states; t Hooft-Polyakov monopole; Witten effect; SL 2; Z invariance;

    Sammanfattning : We introduce the historical context and motivation for the search for magnetic monopoles or monopole-like objects. Beginning the theoretical part we investigate the properties of groups as they relate to symmetries in physical theories. LÄS MER

  7. 5. Quantization Noise Shaping for LTE Fronthaul Downlink

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

    Författare :Alaa Mahamda; Veereswari Kalyanasundaram; [2017]
    Nyckelord :Technology and Engineering;

    Sammanfattning : The modern mobile networks such as the Cloud Radio Network Access (C-RAN) are developing to deal with upcoming requirements in the current generation $4$\textsuperscript{th} Generation (4G) and the upcoming generation i.e. the $5$\textsuperscript{th} Generation (5G). LÄS MER