教學大綱與進度

課程基本資料：

學年期	課號	課程名稱	階段	學分	時數	修	教師	班級	人	撤	備註
112-1	325070	人工智慧跨域大數據分析之應用	1	3.0	3	★	范書愷 黃乾怡 蔡佩芳	工管三丙	10	0	甲乙丙合開

教學大綱與進度：

教師姓名	范書愷　教師諮商時間(Office Hours)
Email	morrisfan@ntut.edu.tw
最後更新時間	2023-08-22 11:35:40
課程大綱	本課程將使用時下最新生成式人工智慧工具介紹人工智慧原理及其於大數據分析及智慧計算之應用，進行數據預處理，建立並優化訓練模型。課程內容包括監控生產線上各種數據，如產品品質、生產效率等。通過即時警報和提示，幫助管理人員快速識別並解決問題。藉由學習和分析過往的故障記錄和維修日誌，預測和診斷產設備，提供相應的維護建議。幫助企業實現定期維護和檢修，從而減少設備故障率和生產停機時間。進行自動識別和分類缺陷，並提供改進建議，從而提高產品品質和生產效率。 This course makes use of the state-of-the-art (SOTA) tools of generative artificial intelligence (AI) to introduce the principles of artificial intelligence and its applications in big data, including data preprocessing, model building, and AI model hyper-parameterization. The course focuses on various types of production-related data. By monitoring shop floor real-time data, production engineers may quickly identify and resolve abnormalities. By learning and analyzing past failure records and maintenance logs, the system may predict and diagnose production errors and provide predictive schedules for equipment maintenance. It helps companies to find a better balance between equipment failure occurrence and production scheduled downtime. The course includes applications in automatic pattern identification, recognition, and classification to assist decision-makers in improving product quality and production efficiency.
課程進度	Week 1~6 Basic Statistical Forecasting (moving average, exponential smoothing, double exponential smoothing) by Pei-fang Tsai Week 7~12 Machine Learning Algorithm (Decision Tree, Random Forest, Classifiers) by Prof. Chien-Yi Huang Week 13~18 Deep Learning Algorithm (Adaboost, Feature Engineering, Neural Network) by Prof. Shu-Kai Fan
評量方式與標準	出席(30%)，分組競賽(70%)
使用教材、參考書目或其他	【遵守智慧財產權觀念，請使用正版教科書，不得使用非法影印教科書】 使用外文原文書：否 參考書目: Artificial Intelligence: A Modern Approach, Fourth Edition Stuart Russell and Peter Norvig 2021, Pearson, New Jersey
課程諮詢管道	每週一下午四點至六點
課程對應SDGs指標
備註