Please use this identifier to cite or link to this item:
https://hdl.handle.net/2445/215077| Title: | Attention mechanisms in transformers: a new formula with mathematical foundations and enhanced interpretability |
| Author: | Conti, Eddie |
| Director/Tutor: | Vieiro Yanes, Arturo |
| Keywords: | Tractament del llenguatge natural (Informàtica) Processament de dades Xarxes neuronals (Informàtica) Treballs de fi de màster Natural language processing (Computer science) Data processing Neural networks (Computer science) Master's thesis |
| Issue Date: | 9-Jul-2024 |
| Abstract: | [en] Large Language Models (LLMs) are AI systems capable of understanding and generating human language by processing vast amounts of text data. In recent years, specifically from 2017, the use of LLMs significantly increased thanks to the introduction of the Transformer architecture. |
| Note: | Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Curs: 2023-2024. Tutor: Arturo Vieiro Yanes i Oriol Pujol Vila |
| URI: | https://hdl.handle.net/2445/215077 |
| Appears in Collections: | Màster Oficial - Fonaments de la Ciència de Dades Programari - Treballs de l'alumnat |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| tfm_conti_eddie.pdf | Memòria | 1.41 MB | Adobe PDF | View/Open |
| Master-Thesis-UB-main.zip | Codi font | 796.03 kB | zip | View/Open |
This item is licensed under a
Creative Commons License
