PYTHON CODE GENERATION USING DEEP LEARNING

dc.contributor.authorAmirov, Amir
dc.contributor.authorAbdygaliyev, Zhandos
dc.date.accessioned2024-06-13T11:53:44Z
dc.date.available2024-06-13T11:53:44Z
dc.date.issued2024-04-19
dc.description.abstractIn this project, it is proposed to develop a sequence-to-sequence model for Python code generation using deep learning. The aim of this project is to investigate the feasibility of using deep learning to generate functional Python code automatically. It discusses the project’s objectives, methodology, initial findings, and ethical considerations. This report references relevant literature. The significance of this project lies in its attempt to offer a model with a specific task and higher efficiency than general-purpose models.en_US
dc.identifier.citationAmirov, A. (2024). Python Code Generation Using Deep Learning. Nazarbayev University School of Engineering and Digital Sciencesen_US
dc.identifier.urihttp://nur.nu.edu.kz/handle/123456789/7865
dc.language.isoenen_US
dc.publisherNazarbayev University School of Engineerning and Digital Sciencesen_US
dc.rightsAttribution-NonCommercial-ShareAlike 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/us/*
dc.subjectType of access: Open Accessen_US
dc.subjectCode generationen_US
dc.subjectdeep learningen_US
dc.subjecttransformeren_US
dc.subjectsequence-to-sequence modelen_US
dc.titlePYTHON CODE GENERATION USING DEEP LEARNINGen_US
dc.typeBachelor's thesisen_US
workflow.import.sourcescience

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Zollanvari_Amirov_FINAL_REPORT.pdf
Size:
749.71 KB
Format:
Adobe Portable Document Format
Description:
capstone project