| DC 欄位 |
值 |
語言 |
| DC.contributor | 軟體工程研究所 | zh_TW |
| DC.creator | 陳正浩 | zh_TW |
| DC.creator | Zheng-Hao Chen | en_US |
| dc.date.accessioned | 2024-7-30T07:39:07Z | |
| dc.date.available | 2024-7-30T07:39:07Z | |
| dc.date.issued | 2024 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:444/thesis/view_etd.asp?URN=111525008 | |
| dc.contributor.department | 軟體工程研究所 | zh_TW |
| DC.description | 國立中央大學 | zh_TW |
| DC.description | National Central University | en_US |
| dc.description.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。 | zh_TW |
| dc.description.abstract | 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. | en_US |
| DC.subject | 自監督學習 | zh_TW |
| DC.subject | 對比學習 | zh_TW |
| DC.subject | 表格資料 | zh_TW |
| DC.subject | 自定義編碼 | zh_TW |
| DC.subject | Self-supervised learnin | en_US |
| DC.subject | Contrastive learnin | en_US |
| DC.subject | tabular data | en_US |
| DC.subject | custom encoding | en_US |
| DC.title | 半監督學習下自定義編碼特徵的大規模比較 | zh_TW |
| dc.language.iso | zh-TW | zh-TW |
| DC.title | A Large-scale Comparison of Customized Feature Encodings under Semi-supervised Learning | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |