Sökning: "Computer science"
Visar resultat 6 - 10 av 883 uppsatser innehållade orden Computer science.
6. Incremental Re-tokenization in BPE-trained SentencePiece Models
Kandidat-uppsats, Umeå universitet/Institutionen för datavetenskapSammanfattning : This bachelor's thesis in Computer Science explores the efficiency of an incremental re-tokenization algorithm in the context of BPE-trained SentencePiece models used in natural language processing. The thesis begins by underscoring the critical role of tokenization in NLP, particularly highlighting the complexities introduced by modifications in tokenized text. LÄS MER
7. A type-driven approach for sensitivity checking with branching
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : Differential Privacy (DP) is a promising approach to allow privacy preserving statistics over large datasets of sensitive data. It works by adding random noise to the result of the analytics. Understanding the sensitivity of a query is key to add the right amount of noise capable of protecting privacy of individuals in the dataset. LÄS MER
8. Ensuring the Security of PyPI Packages
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : Developers often use open-source code libraries in order to achieve desired functionalities without needing to re-implement existing code. Python developers are no exceptions here, and frequently use the Python Package Index, PyPI, to download the specific code packages they want to use. LÄS MER
9. Applying ChatGPT in AI-based dynamic video game narrative generation system
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : ChatGPT’s release and general availability has the potential to create new possibilities for storytelling in games. There are potential benefits of leveraging ChatGPT to generate a narrative at runtime in a video game, as well as possible resulting pitfalls. LÄS MER
10. Improving echocardiogram view classification using diffusion models
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : In the field of medical science datasets are often highly imbalanced, where rare datapoints are of high importance. This study aims to explore the usage of synthetic datasets to improve the classification of echocardiogram views. LÄS MER