Sökning: "Simon Keisala"

Hittade 2 uppsatser innehållade orden Simon Keisala.

  1. 1. Using a Character-Based Language Model for Caption Generation

    Master-uppsats, Linköpings universitet/Interaktiva och kognitiva system

    Författare :Simon Keisala; [2019]
    Nyckelord :Natural Language Processing; NLP; Machine Learning; ML; Neural Network; Caption Generation; Deep Learning; Recurrent Neural Network; Long-Short-Term-Memory; LSTM; word2vec; Language Model;

    Sammanfattning : Using AI to automatically describe images is a challenging task. The aim of this study has been to compare the use of character-based language models with one of the current state-of-the-art token-based language models, im2txt, to generate image captions, with focus on morphological correctness. LÄS MER

  3. 2. Designing an Artificial Neural Network for state evaluation in Arimaa : Using a Convolutional Neural Network

    M1-uppsats, Linköpings universitet/Artificiell intelligens och integrerade datorsystem

    Författare :Simon Keisala; [2017]
    Nyckelord :neural network; machine learning; arimaa; evaluation; reinforcement learning; convolutional neural network;

    Sammanfattning : Agents being able to play board games such as Tic Tac Toe, Chess, Go and Arimaa has been, and still is, a major difficulty in Artificial Intelligence. For the mentioned board games, there is a certain amount of legal moves a player can do in a specific board state. LÄS MER