Sökning: "code-generation"

Visar resultat 1 - 5 av 96 uppsatser innehållade ordet code-generation.

  1. 1. MLIR-based Code Generation for High-Performance Machine Learning on AArch64

    Master-uppsats, Lunds universitet/Institutionen för datavetenskap

    Författare :Johanna Gustafson; [2024]
    Nyckelord :Technology and Engineering;

    Sammanfattning : .... LÄS MER

  3. 2. Machine Learning Based Code Generation of Security Patches

    Master-uppsats, Lunds universitet/Institutionen för datavetenskap

    Författare :Ewada Tsang; Cecilia Huang; [2023]
    Nyckelord :Technology and Engineering;

    Sammanfattning : .... LÄS MER

  4. 3. Code Generation for Accelerating Data Flow : Enhancing Pentaho Data Integration Performance

    Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för fysik

    Författare :Alexander Svensson; [2023]
    Nyckelord :;

    Sammanfattning : Pentaho Data Integration, called Kettle, is an ETL tool that functions as a no-code program. The tool, implemented in Java, enables users to create data flow structures via a graphical user interface and store them as XML files, which can be edited or executed. LÄS MER

  5. 4. Implicit Message Integrity Provision : In Heterogeneous Vehicular Systems

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

    Författare :Paul Molloy; [2023]
    Nyckelord :Privacy; Code Generation; Vehicle-to-infrastructure; Vehicular ad hoc Networks; Standardization; Remote Procedure Calls; Safety; Integritet; Kodgenerering; Fordon-till-infrastruktur; Ad hoc-nät för Fordon; Standardisering; Samtal om fjärrprocedur; Säkerhet;

    Sammanfattning : Vehicles on the road today are complex multi-node computer networks. Security has always been a critical issue in the automotive computing industry. It is becoming even more crucial with the advent of autonomous vehicles and driver assistant technology. There is potential for attackers to control vehicles maliciously. LÄS MER

  7. 5. The impact of task specification on code generated via ChatGPT

    Kandidat-uppsats, Högskolan i Skövde/Institutionen för informationsteknologi

    Författare :Jonathan Lundblad; Edwin Thörn; Linus Thörn; [2023]
    Nyckelord :Code generation; task specification; prompt engineering; ChatGPT; human evaluation; code similarity;

    Sammanfattning : ChatGPT has made large language models more accessible and made it possible to code using natural language prompts. This study conducted an experiment comparing prompt engineering techniques called task specification and investigated their impacton code generation in terms of correctness and variety. LÄS MER