Sökning: "loss in transformer"

Visar resultat 1 - 5 av 47 uppsatser innehållade orden loss in transformer.

  1. 1. Inductive fast charging of IoT devices : An in-depth analysis of short-range wireless charging technologies based on induction

    Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för fysik

    Författare :Franz Wikner; [2024]
    Nyckelord :Electromagnetic power transfer; Inductive power transfer; Short distance WPT;

    Sammanfattning : In the era of Internet of things (IoT), sensor-equipped devices exchange data over networks. In battery powered IoT devices, the lifespan of the devices is often much longer than the battery life, leading to multiple costly and environmentally hazardous battery replacements during the operational life of the devices. LÄS MER

  3. 2. Visual Bird's-Eye View Object Detection for Autonomous Driving

    Master-uppsats, Linköpings universitet/Datorseende

    Författare :Erik Lidman; [2023]
    Nyckelord :computer vision; machine learning; neural networks; deep learning; autonomous driving; autonomous systems; datorseende; maskininlärning; neuronnät; djupinlärning; autonom körning; autonoma system;

    Sammanfattning : In the field of autonomous driving a common scenario is to apply deep learningmodels on camera feeds to provide information about the surroundings. A recenttrend is for such vision-based methods to be centralized, in that they fuse imagesfrom all cameras in one big model for a single comprehensive output. LÄS MER

  4. 3. Disambiguating Italian homographic heterophones with SoundChoice and testing ChatGPT as a data-generating tool

    Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

    Författare :Matilde Nanni; [2023]
    Nyckelord :ChatGPT; Homograph disambiguation; Italian; SoundChoice;

    Sammanfattning : Text-To-Speech systems are challenged by the presence of homographs, words that have more than one possible pronunciation. Rule-based approaches are often still the preferred solution to this issue in the industry. LÄS MER

  5. 4. A Deep Learning approach to Analysing Multimodal User Feedback during Adaptive Robot-Human Presentations : A comparative study of state-of-the-art Deep Learning architectures against high performing Machine Learning approaches

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

    Författare :Manuel Fraile Rodríguez; [2023]
    Nyckelord :Human Feedback; Deep Learning; Convolutional Neural Networks; Transformers; Mänsklig återmatning; mänsklig feedback; djupinlärning; CNN; transformer;

    Sammanfattning : When two human beings engage in a conversation, feedback is generally present since it helps in modulating and guiding the conversation for the involved parties. When a robotic agent engages in a conversation with a human, the robot is not capable of understanding the feedback given by the human as other humans would. LÄS MER

  7. 5. Design Extractor: A ML-based Tool for CapturingSoftware Design Decisions

    Kandidat-uppsats, Mittuniversitetet/Institutionen för kommunikation, kvalitetsteknik och informationssystem (2023-)

    Författare :Petrus Söderström; [2023]
    Nyckelord :machine learning; natural language processing; design decisions; software design; voice recognition;

    Sammanfattning : Context: A software project’s success; involvinga larger group of individuals, relies on efficient teamcommunication. Part of efficient communication is avoidingmiscommunication, misunderstandings, and losingknowledge. These consequences of poor communication canlead to negative repercussions such as loss of time, money,and customer approval. LÄS MER