Sökning: "fashion algorithms"

Visar resultat 16 - 20 av 42 uppsatser innehållade orden fashion algorithms.

  1. 16. Comparing Catastrophic Interference between Incremental Moment Matching-Mean and Hard Attention to the Task

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

    Författare :Quintus Roos; William Lilliesköld; [2020]
    Nyckelord :;

    Sammanfattning : When a neural networks trained on data to solve one problem is trained on new data to solve another problem it tends to forget what it had previously knew that made it able to solve the first problem. This phenomenon is called Catastrophic Interference. LÄS MER

  3. 17. A Reward-based Algorithm for Hyperparameter Optimization of Neural Networks

    Master-uppsats, Karlstads universitet/Institutionen för matematik och datavetenskap (from 2013)

    Författare :Olov Larsson; [2020]
    Nyckelord :Convolutional Neural Networks; Reinforcement Learning; Hyperparameter Optimization; Faltande Neurala Nätverk; Förstärkningsinlärning; Hyperparameteroptimering;

    Sammanfattning : Machine learning and its wide range of applications is becoming increasingly prevalent in both academia and industry. This thesis will focus on the two machine learning methods convolutional neural networks and reinforcement learning. LÄS MER

  4. 18. Constructing a Context-aware Recommender System with Web Sessions

    H-uppsats,

    Författare :Albin Bramstång; Yanling Jin; [2019-07-03]
    Nyckelord :Informations- och kommunikationsteknik; Data- och informationsvetenskap; Information Communication Technology; Computer and Information Science;

    Sammanfattning : During the last decade, the importance of recommender systems has been increasing to the point that the success of many well-known service providers depends on these technologies. Recommender systems can assist people in their decision making process by anticipating preferences. LÄS MER

  5. 19. ASSESSMENT OF ROSLYN ANALYZERS FOR VISUAL STUDIO

    Kandidat-uppsats, Umeå universitet/Institutionen för datavetenskap

    Författare :Jürgen Sundström; [2019]
    Nyckelord :;

    Sammanfattning : So‰ware security is an ever growing subject that is gett‹ing more important as we implement more soft‰ware into our daily lives. We want to protect our personal information and keep our privacy intact. LÄS MER

  7. 20. New Methodologies for Fashion Recommender Systems

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

    Författare :Gabriele Prato; [2019]
    Nyckelord :;

    Sammanfattning : Traditional Recommender Systems rely on finding similarities between users and/or between items. In its broadest definition, a Recommender System tries to predict the preference a user would give to an item. LÄS MER