Sökning: "transformer models"

Visar resultat 1 - 5 av 80 uppsatser innehållade orden transformer models.

  1. 1. ANALYZING THE IMPACT OF PHOTOVOLTAIC AND BATTERIE SYSTEMS ON THE LIFE OF A DISTRIBUTION TRANSFORMER

    Master-uppsats, Mälardalens högskola/Akademin för ekonomi, samhälle och teknik

    Författare :Mohamed Mohamed Ali; [2021]
    Nyckelord :Distribution Transformer; PV Penetration; BESS; Self-Consumption; Peak Shaving; HSP; ONAN; Thermal Model; RPF; Paper Insulation; Oil Immersed Transformers.;

    Sammanfattning : This degree project presents a study case in Eskilstuna-Sweden, regarding the effect of the photovoltaic (PV) systems with battery energy storage system (BESS) on a power distribution transformer, and how they could change the transformer lifespan. For that, an extensive literature review has been conducted, and two MATLAB models were used to simulate the system. LÄS MER

  2. 2. Tree positional encodings for transformer models on HTML DOM tree element classification : Enabling structurally aware transformer models through positional encodings to improve performance on an HTML element classification problem

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

    Författare :Gustave Rousselet; [2021]
    Nyckelord :Transformer; Positional Encoding; HTML; DOM; Tree; Element; Transformer; Positionskodning; HTML; DOM; Träd; Element;

    Sammanfattning : With the continued proliferation of access and the usage of the internet, the field of web learning is continuously growing in order to automate and improve parts of our experience on the web. Research in web learning has often lagged behind its counterparts in Natural Language Processing (NLP), novel methods often reach adoption in web learning research with a delay. LÄS MER

  3. 3. Multi-task regression QSAR/QSPR prediction utilizing text-based Transformer Neural Network and single-task using feature-based models

    Master-uppsats, Linköpings universitet/Statistik och maskininlärning

    Författare :Spyridon Dimitriadis; [2021]
    Nyckelord :multi-task regression; QSAR; QSPR; deep learning; attention based models; transfer learning;

    Sammanfattning : With the recent advantages of machine learning in cheminformatics, the drug discovery process has been accelerated; providing a high impact in the field of medicine and public health. Molecular property and activity prediction are key elements in the early stages of drug discovery by helping prioritize the experiments and reduce the experimental work. LÄS MER

  4. 4. Simplified Model For Simulation of Fault Ride Through at Hydropower Units

    Master-uppsats, Uppsala universitet/Institutionen för fysik och astronomi

    Författare :Sebastian Söderström; [2021]
    Nyckelord :Fault Ride Through; Hydropower; Simulation; Generator; Simulink; Transient Stability; Gränsbryttid; Vattenkraft; Simulering; Generator; Simulink; Transient Stabilitet;

    Sammanfattning : As new requirements for grid connected generators were implemented, the requirements for evaluating the Fault Ride Through capabilities of the generators became stricter. When refurbishing a power unit, proof that the power unit meet the requirements must be submitted to the authorities. LÄS MER

  5. 5. Maskininlärning för automatisk extrahering av citat från recensioner : Med användning av BERT, Inter-Sentence Transformer och artificiella neuronnätverk

    M1-uppsats, KTH/Hälsoinformatik och logistik; KTH/Hälsoinformatik och logistik

    Författare :Clara Hällgren; Alexander Kristiansson; [2021]
    Nyckelord :Machine Learning; BERT; ATS; Automatic Text Summary; Extractive Summary; Inter-Sentence Transformer; Artificial Neural Network.; Maskininlärning; BERT; ATS; automatisk textsummering; extraktiv summering; Inter-Sentence Transformer; artificiella neuronnät.;

    Sammanfattning : Att manuellt välja en eller flera meningar ur en filmrecension att använda som citat kan vara en tidskrävande uppgift. Denna rapport utvärderar övervakade maskininlärningsmodeller för att skapa en prototyp som automatiskt kan välja lämpliga citat ur recensioner. LÄS MER