Essays about: "Djupinlärning"

Found 4 essays containing the word Djupinlärning.

  1. 1. Application of Deep Q-learning for Vision Control on Atari Environments

    University essay from Lunds universitet/Beräkningsbiologi och biologisk fysik

    Author : Jim Öhman; [2021]
    Keywords : Reinforcement learning; Atari 2600; Deep Q-learning; Myopic Agents; Vision Control; Physics and Astronomy;

    Abstract : The success of Reinforcement Learning (RL) has mostly been in artificial domains, with only some successful real-world applications. One of the reasons being that most real-world domains fail to satisfy a set of assumptions of RL theory. READ MORE

  2. 2. Automated visual inspections for final assembly : A case study of cab assembly at Scania Oskarshamn

    University essay from Luleå tekniska universitet/Institutionen för ekonomi, teknik och samhälle; Luleå tekniska universitet/Institutionen för ekonomi, teknik och samhälle

    Author : Amos Johnson; Hannes Aronsson; [2020]
    Keywords : Quality inspections; machine vision; deep neural networks; final assembly; Kvalitetsinspektioner; machine vision; djupinlärning; slutmontering;

    Abstract : Quality inspections have seen varying degrees of automation depending on the complexity of the task and the environment. Especially in later phases of multi-stage manufacturing processes, such as final assembly in automotive industries, quality inspections are largely manual to this day. READ MORE

  3. 3. A Deep Neural Network Approach for Intersection Testing of Two 3D Meshes

    University essay from Blekinge Tekniska Högskola/Institutionen för datavetenskap; Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Author : Gustav Björk; Alexander Wester; [2020]
    Keywords : Artificial Intelligence; Collision detection; Separating Axis Theorem; Machine learning; Real-time performance; Artificiell intelligens; Kollisionsdetektering; Separating Axis Theorem; Maskininlärning; Realtidsprestanda;

    Abstract : Background. Neural Networks have mainly been used in behavior and gameplayrelated areas in games, but they have not yet been used specifically for intersection testing. This thesis explores the possibility to use deep neural networks for intersection testing of two 3D meshes. Objectives. READ MORE

  4. 4. Deep learning-based forecasting of financial assets

    University essay from KTH/Matematisk statistik

    Author : Philip Widegren; [2017]
    Keywords : ;

    Abstract : Deep learning and neural networks has recently become a powerful tool to solve complex problem due to improvements in training algorithms. Examples of successful application can be found in speech recognition and machine translation. READ MORE