半監督學習下自定義編碼特徵的大規模比較;A Large-scale Comparison of Customized Feature Encodings under Semi-supervised Learning

NCUIR > College of Electrical Engineering & Computer Science > Software Engineer > Electronic Thesis & Dissertation > Item 987654321/95299

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/95299

Title:	半監督學習下自定義編碼特徵的大規模比較;A Large-scale Comparison of Customized Feature Encodings under Semi-supervised Learning
Authors:	陳正浩;Chen, Zheng-Hao
Contributors:	軟體工程研究所
Keywords:	自監督學習;對比學習;表格資料;自定義編碼;Self-supervised learnin;Contrastive learnin;tabular data;custom encoding
Date:	2024-07-30
Issue Date:	2024-10-09 16:38:20 (UTC+8)
Publisher:	國立中央大學
Abstract:	自定義編碼方式可有效提升深度學習模型在監督式任務的表現，但自定義編碼方式在自監督對比學習的效果則尚未被大規模驗證。本論文設計並實現了一個靈活的自定義特徵編碼框架，讓研究者可以大規模比較比較不同編碼方式在自監督任務的效果。同時，我們提出了一種新的編碼方式，探索其在不同資料集上的潛力和應用價值。;Custom encoding methods can effectively enhance the performance of deep learning models in supervised tasks. However, custom encoding′s effectiveness in self-supervised contrastive learning has yet to be extensively validated. This paper designs and implements a flexible framework for custom feature encoding evaluation, allowing researchers to comprehensively compare the effects of different encoding methods on self-supervised tasks. Additionally, we propose a new encoding method to explore its potential and application value across various datasets.
Appears in Collections:	[Software Engineer] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	43	View/Open

社群 sharing

Loading...