Sökning: "github"

Visar resultat 6 - 10 av 157 uppsatser innehållade ordet github.

  1. 6. The Impact of AI-generated Code on Web Development: A Comparative Study of ChatGPT and GitHub Copilot

    Kandidat-uppsats, Blekinge Tekniska Högskola/Institutionen för programvaruteknik

    Författare :Edvin Fajkovic; Erik Rundberg; [2023]
    Nyckelord :ChatGPT; Copilot; Ethics; GPT-3; Codex;

    Sammanfattning : Background. Machine learning and artificial intelligence are advancing faster than ever, code generation is becoming a hot topic and is starting to gain traction in the industry. This creates the question, is it possible to create a complete website from scratch using only code generated by AI? Objectives. LÄS MER

  3. 7. Mitigating Unintended Bias in Toxic Comment Detection using Entropy-based Attention Regularization

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

    Författare :Fabio Camerota; [2023]
    Nyckelord :XLNet; BERT; Toxic Comment Classification; Entropy-based Attention Regularization; XLNet; BERT; Toxisk Kommentar Klassificering; Entropibaserad uppmärksamhetsreglering;

    Sammanfattning : The proliferation of hate speech is a growing challenge for social media platforms, as toxic online comments can have dangerous consequences also in real life. There is a need for tools that can automatically and reliably detect hateful comments, and deep learning models have proven effective in solving this issue. LÄS MER

  4. 8. Dataset characteristics effect on time series forecasting : comparison of statistical and deep learning models

    Kandidat-uppsats, Högskolan i Halmstad/Akademin för informationsteknologi

    Författare :Adam Ahlman; Adam Taylor; [2023]
    Nyckelord :Time Series; Forecasting;

    Sammanfattning : Time series are points of data measured throughout time in equally spaced periods. They present characteristics such as level, noise, trend, seasonality, and outliers. Time series forecasting is the attempt to predict single or multiple future values. LÄS MER

  5. 9. Evaluation of Rust Codebases Using Public Information

    Master-uppsats, Lunds universitet/Institutionen för datavetenskap

    Författare :Emil Eriksson; [2023]
    Nyckelord :Rust; Code Evaluation; Open Source; Crates.io; Cargo; GraphQL; Query; Dependencies; Technology and Engineering;

    Sammanfattning : Understanding the content of a software project is a complex endeavour. While the Rust programming language promises developers a safer programming language, a program may still include vulnerable code through its dependencies. LÄS MER

  7. 10. Context-aware Swedish Lexical Simplification : Using pre-trained language models to propose contextually fitting synonyms

    Kandidat-uppsats, Linköpings universitet/Institutionen för datavetenskap

    Författare :Emil Graichen; [2023]
    Nyckelord :automatic text simplification; lexical simplification; Swedish; BERT; GPT-3; evaluation dataset; synonymy;

    Sammanfattning : This thesis presents the development and evaluation of context-aware Lexical Simplification (LS) systems for the Swedish language. In total three versions of LS models, LäsBERT, LäsBERT-baseline, and LäsGPT, were created and evaluated on a newly constructed Swedish LS evaluation dataset. LÄS MER