Sökning: "neurala nätverk"

Visar resultat 1 - 5 av 627 uppsatser innehållade orden neurala nätverk.

  1. 1. Attention based Knowledge Tracing in a language learning setting

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

    Författare :Sebastiaan Vergunst; [2022]
    Nyckelord :Knowledge Tracing; Exercise Recommendation; Personalised Learning; Recurrent Neural Network; Attention; Self-Attention; Exercise Embedding; Kunskapsspårning; Övningsrekommendation; Personligt Anpassad Inlärning; Rekurrenta Neurala Nätverk; Uppmärksamhet; Självuppmärksamhet; Övningsembedding;

    Sammanfattning : Knowledge Tracing aims to predict future performance of users of learning platforms based on historical data, by modeling their knowledge state. In this task, the target is a binary variable representing the correctness of the exercise, where an exercise is a word uttered by the user. LÄS MER

  2. 2. Credit Scoring Based on Behavioural Data

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

    Författare :Daniel Bouvin; Erik Hamberg; [2022]
    Nyckelord :Banking; Behavior; Behaviour; Credit Modelling; Klarna; Logistic Regression; Machine Learning; Neural Networks; Random Forests; XGBoost;

    Sammanfattning : Credit modelling has traditionally been done by credit institutes based on financial data about the individuals requesting the credit. While this has been sufficient in lowering risk in developed economies with plenty of financial data it is inefficient in developing economies and fails to reach the unbanked population. LÄS MER

  3. 3. Investigating Relations between Regularization and Weight Initialization in Artificial Neural Networks

    Kandidat-uppsats, Lunds universitet/Beräkningsbiologi och biologisk fysik

    Författare :Rasmus Sjöö; [2022]
    Nyckelord :Artificial Neural Networks; L1 Regularization; L2 Regularization; Loss Function; Maximum Likelihood; Regularization Strength Synthetic Data Generation; Weight Initialization; Physics and Astronomy;

    Sammanfattning : L2 regularization is a common method used to prevent overtraining in artificial neural networks. However, an issue with this method is that the regularization strength has to be properly adjusted for it to work as intended. This value is usually found by trial and error which can take some time, especially for larger networks. LÄS MER

  4. 4. Probabilistic Forecasting through Reformer Conditioned Normalizing Flows

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

    Författare :Samuel Norling; [2022]
    Nyckelord :;

    Sammanfattning : Forecasts are essential for human decision-making in several fields, such as weather forecasts, retail prices, or stock predictions. Recently the Transformer neural network, commonly used for sequence-to-sequence tasks, has shown great potential in achieving state-of-the-art forecasting results when combined with density estimations models such as Autoregressive Flows. LÄS MER

  5. 5. Precipitation Nowcasting using Deep Neural Networks

    Master-uppsats, KTH/Fysik

    Författare :Valter Fallenius; [2022]
    Nyckelord :Deep Neura Networks; Artificial Intelligence; Meteorology; Precipitationa Nowcasting; Djupa neurala nätverk; artificiell intelligens; nederbördsprognoser; meteorologi;

    Sammanfattning : Deep neural networks (DNNs) based on satellite and radar data have shown promising results for precipitation nowcasting, beating physical models and optical flow for time horizons up to 8 hours. “MetNet”, developed by Google AI, is a 225 million parameter DNN combining three different types of architectures that was trained on satellite and radar data over the United States. LÄS MER