Sökning: "Feed Forward Neural Networks"

Visar resultat 11 - 15 av 57 uppsatser innehållade orden Feed Forward Neural Networks.

  1. 11. Transformer learning for traffic prediction in mobile networks

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

    Författare :Daniel Wass; [2021]
    Nyckelord :Transformer; Attention; LSTM; Mobile traffic prediction.; Transformer; Attention; LSTM; Prediktering av mobil nätverkstrafik.;

    Sammanfattning : The resources of mobile networks are expensive and limited, and as demand for mobile data continues to grow, improved resource utilisation is a prioritised issue. Traffic demand at base stations (BSs) vary throughout the day and week, but the capacity remains constant and utilisation could be significantly improved based on precise, robust, and efficient forecasting. LÄS MER

  3. 12. AI-based Classification of Radar Signals

    Master-uppsats, Lunds universitet/Matematisk statistik

    Författare :Ludwig Hollmann; Max Fors Joki; [2021]
    Nyckelord :Neural networks; TensorFlow; Keras; Radar signals; Mathematics and Statistics;

    Sammanfattning : Military vehicles typically send out radar signals in order to detect their surroundings. Using an Electromagnetic Support Measures receiver, these can be detected and it is of interest to be able to classify them in order to identify the vehicle and type of radar. LÄS MER

  4. 13. Machine Learning Modeling using Heterogeneous Transfer Learning in the Edge Cloud

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

    Författare :Fernando Garcia Sanz; [2021]
    Nyckelord :Deep learning; Edge cloud; Heterogeneous transfer learning; Machine Learning; Service performance; ; Deep learning; Edge cloud; heterogen överföringsinlärning; maskininlärning; serviceprestanda; ;

    Sammanfattning : The dynamic nature of the edge cloud and future network infrastructures is another challenge to be added when modeling end-to-end service performance using machine learning. That is, a model that has been trained for one specific environment may see reductions in prediction accuracy over time due to e.g., routing, migration, or scaling decisions. LÄS MER

  5. 14. Comparison of linear regression and neural networks for stock price prediction

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Signaler och system

    Författare :Nils Karlsson; [2021]
    Nyckelord :Stock market; Stock market prediction; prediction; neural network; feed forward neural network; artificial neural network; linear regression; finance; efficient market hypothesis; EMH;

    Sammanfattning : Stock market prediction has been a hot topic lately due to advances in computer technology and economics. One economic theory, called Efficient Market Hypothesis (EMH), states that all known information is already factored into the prices which makes it impossible to predict the stock market. LÄS MER

  7. 15. Machinery Health Indicator Construction using Multi-objective Genetic Algorithm Optimization of a Feed-forward Neural Network based on Distance

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

    Författare :Jacob Nyman; [2021]
    Nyckelord :Prognostics; Health Indicator Construction; Remaining Useful Life Prediction; Multi-objective Optimization; Distance; Prognostik; Hälsoindikatorkonstruktion; Återstående Livslängd; Multiobjektiv Optimering; Avstånd;

    Sammanfattning : Assessment of machine health and prediction of future failures are critical for maintenance decisions. Many of the existing methods use unsupervised techniques to construct health indicators by measuring the disparity between the current state and either the healthy or the faulty states of the system. LÄS MER