Sökning: "Error"

Visar resultat 1 - 5 av 2774 uppsatser innehållade ordet Error.

  1. 1. Traceability of Human Error Production Defects in Automotive Manufacturing

    Kandidat-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Chiara Lucatello; Chatchai Sornkarn; [2019-11-12]
    Nyckelord :Error detection; in-and-out; logging process; Inputting process; Technological frames; Usability; Traceability; Process improvement; Factory automation;

    Sammanfattning : Many global automotive industries have movedtowards factory automation, yet several still rely on collectingmanual data from the plant floor and manually inputting thedata into the management quality system in the assembly line. Inthis case study research, the objective of our study was to observehow technology advancement can be supported for human errorlogging in the quality assurance process. LÄS MER

  2. 2. AI Safe Exploration: Reinforced learning with a blocker in unsafe environments

    Kandidat-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Marco Koivisto; Philip Crockett; Axel Spångberg; [2019-11-12]
    Nyckelord :Artificial Intelligence; Reinforcement learning; Safe exploration; Blocker; Machine Learning; Baby AI Game; Gym Mini Grid;

    Sammanfattning : Artificial intelligence can be trained with a trial anderror based approach. In an environment where a catastrophecan not be accepted a human overseer can be used, but thismight lower the efficiency of the learning. LÄS MER

  3. 3. Learning Geometry Compatibility with 3D Convolutional Neural Networks

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Florian Stellbrink; [2019-10-04]
    Nyckelord :computer science; computer graphics; machine learning; geometry; voxel; thesis;

    Sammanfattning : Modern video games oer substantial amounts of customization options. Manually testing the visual compatibility of all options is time-consuming and error-prone. Together with Ghost Games, we present a method of learning the visual compatibility between pairs of geometries. LÄS MER

  4. 4. Multi Agent Reinforcement Learning

    Master-uppsats, Göteborgs universitet/Institutionen för matematiska vetenskaper

    Författare :Rikard Isaksson; [2019-06-13]
    Nyckelord :;

    Sammanfattning : Machine learning and artificial intelligence has been a hot topic the last few years, thanks to improved computational power the machine learning framework can now be applied to larger data sets. Reinforcement learning is a group of machine learning algorithms where one does not know the correct answer in advance, much like unsupervised learning. LÄS MER

  5. 5. Automatic refactoring for Agda

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Karin Wibergh; [2019-04-24]
    Nyckelord :Agda; dependent types; refactoring; thesis;

    Sammanfattning : The task of making changes to an existing code base to improve performance, legibility,or extensibility while preserving behaviour is important to virtually anyprogram. Many times this involves making changes requiring a great deal of typingin various places, which is tedious and error-prone. LÄS MER