Sökning: "Sami Purmonen"

Hittade 2 uppsatser innehållade orden Sami Purmonen.

  1. 1. Predicting Game Level Difficulty Using Deep Neural Networks

    Master-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Sami Purmonen; [2017]
    Nyckelord :Deep learning; neural networks; machine learning;

    Sammanfattning : We explored the usage of Monte Carlo tree search (MCTS) and deep learning in order to predict game level difficulty in Candy Crush Saga (Candy) measured as number of attempts per success. A deep neural network (DNN) was trained to predict moves from game states from large amounts of game play data. LÄS MER

  3. 2. Testing Stock Market Efficiency Using Historical Trading Data and Machine Learning

    Kandidat-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Sami Purmonen; Paul Griffin; [2015]
    Nyckelord :;

    Sammanfattning : Stock forecasting is a problem that is important in finance because it aids investors in financial decision making. According to the efficient market hypothesis stock markets are efficient in such a way that it's impossible to gain excess returns over the market by making decisions based on current available information. LÄS MER