Sökning: "Onlineinlärning"

Visar resultat 1 - 5 av 6 uppsatser innehållade ordet Onlineinlärning.

  1. 1. Real-time Unsupervised Domain Adaptation

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

    Författare :Marc Botet Colomer; [2023]
    Nyckelord :Unsupervised Domain Adaptation; Real-Time applications; Online Learning; Self-Learning; Semantic Segmentation; Reinforcement Learning; Oövervakad domänanpassning; Realtidsapplikationer; Onlineinlärning; Självinlärning; Semantisk Segmentering; Förstärkningsinlärning;

    Sammanfattning : Machine learning systems have been demonstrated to be highly effective in various fields, such as in vision tasks for autonomous driving. However, the deployment of these systems poses a significant challenge in terms of ensuring their reliability and safety in diverse and dynamic environments. LÄS MER

  3. 2. Voltage-Based Multi-step Prediction : Data Labeling, Software Evaluation, and Contrasting DRL with Traditional Prediction Methods

    Uppsats för yrkesexamina på grundnivå, Högskolan i Halmstad/Akademin för informationsteknologi

    Författare :Joakim Svensson; [2023]
    Nyckelord :Deep Reinforcement Learning; Multi-step Prediction; Time Series Forecasting; Djup Förstärkningsinlärning; Flerstegsprognos; Tidsserieprognos;

    Sammanfattning : In this project, three primary problems were addressed to improve battery data management and software performance evaluation. All solutions used voltage values in time together with various device characteristics. Battery replacement labeling was performed using Hidden Markov Models. LÄS MER

  4. 3. Online Sample Selection for Resource Constrained Networked Systems

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

    Författare :Philip Sjösvärd; Samuel Miksits; [2022]
    Nyckelord :Online learning; Sample Selection; Real-time Learning; Random Forest; Reservoir Sampling; Relevance and Redundancy; Binned Distribution; Autoregressive Model; Change Detection; Model Re-computation;

    Sammanfattning : As more devices with different service requirements become connected to networked systems, such as Internet of Things (IoT) devices, maintaining quality of service becomes increasingly difficult. Large data sets can be obtained ahead of time in networks to train prediction models offline, however, resulting in high computational costs. LÄS MER

  5. 4. Data-driven Discovery of Real-time Road Compaction Parameters

    Master-uppsats, KTH/Matematisk statistik

    Författare :Yuqi Shao; [2022]
    Nyckelord :statistics; machine learning; road compaction; statistik; maskininlärning; vägpackning;

    Sammanfattning : Road compaction is the last and important stage in road construction. Both under-compaction and over-compaction are inappropriate and may lead to road failures. Intelligent compactors has enabled data gathering and edge computing functionalities, which introduces possibilities in data-driven compaction control. LÄS MER

  7. 5. Using Machine Learning to Predict Form Processing Times : Applied to Swedish pay-as-you-earn tax returns

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

    Författare :Staffan Al-Kadhimi; [2022]
    Nyckelord :Machine Learning; Regression; Time Estimation; Forms; Maskininlärning; Regression; Tidsestimering; Formulär;

    Sammanfattning : Forms are used in many situations. For example, they tend to be ubiquitous in communications between individuals and government agencies. Something which could potentially boost transparency and efficiency is accurate estimates of how long it will take for the receiver to process a given completed form. LÄS MER