Sökning: "meta-learning"

Visar resultat 1 - 5 av 8 uppsatser innehållade ordet meta-learning.

  1. 1. EXPLORING TEST CASE DESIGN APPROACHES FOR META-LEARNING MODELS

    Magister-uppsats, Mälardalens universitet/Akademin för innovation, design och teknik

    Författare :Farzaneh Alsadat Seyedshahi; [2022]
    Nyckelord :Meta-learning; Test;

    Sammanfattning : Meta-learning, which allows individuals to learn from a collection of algorithms, is currently one of the most essential and cutting-edge deep-learning issues. Because of their widespread applicability, these algorithms are inextricably linked to essential systems and human lives, and the necessity to test and debug such crucial systems is apparent. LÄS MER

  3. 2. A Systematic Literature Review on Meta Learning for Predictive Maintenance in Industry 4.0

    Kandidat-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

    Författare :Ahmet Fisenkci; [2022]
    Nyckelord :Meta-learning; Few-Shot; Predictive Maintenance; Industry 4.0; Fault detection; Fault Prognostics; Fault Diagnosis;

    Sammanfattning : Recent refinements in Industry 4.0 and Machine Learning demonstrate the positive effects of using deep learning models for intelligent maintenance. The primary benefit of Deep Learning (DL) is its capability to extract attributes and make fast, accurate, and automated predictions without supervision. LÄS MER

  4. 3. Cyberattacker - unika fall eller en möjlighet till lärande? : En kvalitativ fallstudie av den nationella hanteringen av cyberattacker inom Sverige

    Kandidat-uppsats, Försvarshögskolan

    Författare :Olivia Malmström; [2021]
    Nyckelord :;

    Sammanfattning : In the last decades the world has become more and more digitalized which has led to a new kind of threat, known as cyberattacks. The statistics show that the amount of attacks are increasing every year even though the increasing experience should help to contain the threat. LÄS MER

  5. 4. Insights into Model-Agnostic Meta-Learning on Reinforcement Learning Tasks

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

    Författare :Konstantinos Saitas-Zarkias; [2021]
    Nyckelord :Meta-Learning; Reinforcement Learning; Deep Learning;

    Sammanfattning : Meta-learning has been gaining traction in the Deep Learning field as an approach to build models that are able to efficiently adapt to new tasks after deployment. Contrary to conventional Machine Learning approaches, which are trained on a specific task (e. LÄS MER

  7. 5. Model-Agnostic Meta-Learning for Digital Pathology

    Master-uppsats, Linköpings universitet/Datorseende

    Författare :Freja Fagerblom; [2020]
    Nyckelord :machine learning; model-agnostic meta-learning; maml; digital pathology; histopathology; meta learning; her2; domain shift;

    Sammanfattning : The performance of conventional deep neural networks tends to degrade when a domain shift is introduced, such as collecting data from a new site. Model-Agnostic Meta-Learning, or MAML, has achieved state-of-the-art performance in few-shot learning by finding initial parameters that adapt easily for new tasks. LÄS MER