請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81340完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 藍俊宏(Jakey Blue) | |
| dc.contributor.author | Yun Chu | en |
| dc.contributor.author | 褚芸 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:44:12Z | - |
| dc.date.available | 2026-08-01 | |
| dc.date.available | 2022-11-24T03:44:12Z | - |
| dc.date.copyright | 2021-08-04 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-07-17 | |
| dc.identifier.citation | Anuradha, J. (2015). A brief introduction on Big Data 5Vs characteristics and Hadoop technology. Procedia Computer Science, 48, 319-324. Azarang, A., Manoochehri, H. E., Kehtarnavaz, N. (2019). Convolutional autoencoder-based multispectral image fusion. IEEE Access, 7, 35673-35683. Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K. R., Samek, W. (2015). On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS One, 10(7), e0130140. Bengio, Y., Goodfellow, I., Courville, A. (2017). Deep Learning (Vol. 1). Massachusetts, USA:: MIT press. Böhning, D. (1992). Multinomial logistic regression algorithm. Annals of the Institute of Statistical Mathematics, 44(1), 197-200. Christ, M., Kempa-Liehr, A. W., Feindt, M. (2016). Distributed and parallel time series feature extraction for industrial big data applications. arXiv preprint arXiv:1610.07717. Cortes, C., Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273-297. Cox, D. R. (1958). The regression analysis of binary sequences. Journal of the Royal Statistical Society: Series B (Methodological), 20(2), 215-232. Data Challenge PHM (2016) Society of Prognostic and Health Management. https://www.phmsociety.org/events/conference/phm/16/data-challenge De Mauro, A., Greco, M., Grimaldi, M. (2016). A formal definition of Big Data based on its essential features. Library Review. Fu, L. (2015). The discriminate analysis and dimension reduction methods of high dimension. Open Journal of Social Sciences, 3(03), 7. Fulcher, B. D. (2018). Feature-based time-series analysis. In Feature Engineering for Machine Learning and Data Analytics (pp. 87-116). CRC Press. Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y. (2016). Deep Learning (Vol. 1, No. 2). Cambridge: MIT press. Gunning, D. (2017). Explainable artificial intelligence (xai). Defense Advanced Research Projects Agency (DARPA), nd Web, 2(2). Hotelling, H. (1933). Analysis of a complex of statistical variables into principal components. Journal of Educational Psychology, 24(6), 417. Jain, A. K., Mao, J., Mohiuddin, K. M. (1996). Artificial neural networks: A tutorial. Computer, 29(3), 31-44. Ju, Y., Guo, J., Liu, S. (2015, September). A deep learning method combined sparse autoencoder with SVM. In 2015 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (pp. 257-260). IEEE. LeCun, Y., Bengio, Y. (1995). Convolutional networks for images, speech, and time series. The Handbook of Brain Theory and Neural Networks, 3361(10), 1995. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324. Lore, K. G., Akintayo, A., Sarkar, S. (2017). LLNet: A deep autoencoder approach to natural low-light image enhancement. Pattern Recognition, 61, 650-662. McClelland, J. L., Rumelhart, D. E., PDP Research Group. (1986). Parallel Distributed Processing (Vol. 2, pp. 20-21). Cambridge, MA: MIT press. Ribeiro, M. T., Singh, S., Guestrin, C. (2016, August). ' Why should i trust you?' Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135-1144). Robert, T., Thome, N., Cord, M. (2018). Hybridnet: Classification and reconstruction cooperation for semi-supervised learning. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 153-169). Rosipal, R., Girolami, M., Trejo, L. J., Cichocki, A. (2001). Kernel PCA for feature extraction and de-noising in nonlinear regression. Neural Computing Applications, 10(3), 231-243. Rumelhart, D. E., Hinton, G. E., Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533-536. Sakurada, M., Yairi, T. (2014, December). Anomaly detection using autoencoders with nonlinear dimensionality reduction. In Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis (pp. 4-11). Scholkopf, B., Mika, S., Burges, C. J., Knirsch, P., Muller, K. R., Ratsch, G., Smola, A. J. (1999). Input space versus feature space in kernel-based methods. IEEE Transactions on Neural Networks, 10(5), 1000-1017. Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B (Methodological), 58(1), 267-288. Turek, M. (2018). Explainable artificial intelligence (XAI). Defense Advanced Research Projects Agency. https://www.darpa.mil/program/explainable-artificial-intelligence Vapnik, V., Golowich, S. E., Smola, A. (1997). Support vector method for function approximation, regression estimation, and signal processing. Advances in Neural Information Processing Systems, 281-287. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81340 | - |
| dc.description.abstract | 隨著科技不斷的精進與創新，資料分析不論在資料規模、運算技術和分析方式都帶起了一波典範的轉移，面對來源多樣且結構複雜的資料探勘技術中，特徵工程是至關重要的步驟，目前主流使用的降維技術，多為非監督式學習萃取出保留資訊最大化的特徵，然而其中的特徵並不全然適合於建立分類/迴歸模型，因此本論文以研究此問題為出發點，設計以半監督式的卷積自動編碼器分類/迴歸模型，藉著把卷積自動編碼器的中間層攤平後，再送入分類/迴歸器同步訓練，目標是經由一次訓練即萃取出具備分類/迴歸能力之特徵，使這些特徵不僅有重建原始資料的能力，還能維持分類/迴歸模型預測的準確度。 深度學習技術在近年來獲得許多重要突破，在影像辨識、語音處理、特徵診斷等廣泛應用催生了許多成功案例，因此類神經網路的黑盒子問題也重新受到檢視，面對模型中無法理解的推理過程，將使其應用大大受限。而本論文提出之卷積自動編碼器分類/迴歸模型亦屬深度學習模型，也同樣面對黑盒子無法解釋的困境，因此本研究先回顧當前人工智慧可解釋性之發展，發展演算法拆解已訓練完成的深度神經網路模型，以得出一套對應的特徵解析架構，使提出的特徵萃取模型能夠具備基本的解釋性。 本研究最後使用Fashion MNIST、半導體化學機械研磨製程的兩資料集來驗證提出的特徵萃取模型，並透過視覺化呈現特徵重要性，找出影響模型的關鍵變數，達到模型預測性和可解釋性之間的平衡，提升深度神經網路技術的應用性。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:44:12Z (GMT). No. of bitstreams: 1 U0001-1607202121453400.pdf: 6560877 bytes, checksum: 9c8423fb116b7a6c9c8f7b8546f26309 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 致謝 i 中文摘要 ii Abstract iii 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機與目的 4 1.3 研究架構 6 第二章 文獻探討 7 2.1 非監督式特徵萃取 7 2.1.1 線性降維方法 7 2.1.2 非線性降維方法 8 2.2 分類與迴歸模型之相關研究 11 2.2.1 多元邏輯斯迴歸 11 2.2.2 支援向量機 12 2.2.3 支援向量迴歸 13 2.2.4 類神經網路 14 2.2.5 卷積神經網路 16 2.3 人工智慧可解釋性 19 第三章 發展具分類/迴歸資格之特徵萃取工程 20 3.1 半監督式模型架構 23 3.1.1 模型訓練 24 3.1.2 分類器/迴歸器整合方法 25 3.2 原始重要性變數推論 28 3.2.1 重建路徑原始變數重要性 28 3.2.2 迴歸路徑原始變數重要性 29 3.2.3 批次製程資料處理技術 30 第四章 案例研討 32 4.1 案例一：Fashion MNIST 32 4.1.1 資料集與實驗架構設計 32 4.1.2 模型訓練與參數設定 33 4.1.3 標竿模型之設定 35 4.1.4 模型結果評比 36 4.1.5 解釋性推論結果 40 4.2 案例二：化學機械研磨製程資料 48 4.2.1 資料集與實驗架構設計 48 4.2.2 資料前處裡 50 4.2.3 模型訓練與參數設定 53 4.2.4 標竿模型之設定 54 4.2.5 模型結果評比 55 4.2.6 解釋性推論結果 58 第五章 結論與未來研究建議 69 5.1 研究方法與成效歸納 69 5.2 未來研究建議 70 參考文獻列表 71 | |
| dc.language.iso | zh-TW | |
| dc.subject | 模型可解釋性 | zh_TW |
| dc.subject | 卷積自動編碼器 | zh_TW |
| dc.subject | 卷積神經網路 | zh_TW |
| dc.subject | 特徵萃取 | zh_TW |
| dc.subject | 分類器/迴歸器建模 | zh_TW |
| dc.subject | Convolutional Neural Networks (CNN) | en |
| dc.subject | Explainable AI (XAI) | en |
| dc.subject | Feature Extraction | en |
| dc.subject | Convolutional Autoencoder (CAE) | en |
| dc.subject | Machine Learning Algorithms | en |
| dc.subject | Classifier/Regressor Model | en |
| dc.title | 具分類/迴歸資格之特徵工程與解釋性萃取以利深度分類/迴歸器建模 | zh_TW |
| dc.title | Extraction of Classification/Regression-qualified and Explainable Features for Deep Classifier/Regressor Modeling | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳正剛(Hsin-Tsai Liu),許嘉裕(Chih-Yang Tseng) | |
| dc.subject.keyword | 卷積自動編碼器,卷積神經網路,特徵萃取,分類器/迴歸器建模,模型可解釋性, | zh_TW |
| dc.subject.keyword | Convolutional Autoencoder (CAE),Convolutional Neural Networks (CNN),Feature Extraction,Classifier/Regressor Model,Machine Learning Algorithms,Explainable AI (XAI), | en |
| dc.relation.page | 73 | |
| dc.identifier.doi | 10.6342/NTU202101525 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-07-19 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 工業工程學研究所 | zh_TW |
| dc.date.embargo-lift | 2026-08-01 | - |
| 顯示於系所單位： | 工業工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1607202121453400.pdf 未授權公開取用 | 6.41 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。