Course Syllabus

Course Information：

Year-Semester Course Number Course Name Phase Credits Hours Required/Elective Instructor Class Student NO. Withdraw Note

Spring Semester
Year 2026 356639 Deep Learning and Business Forecasting 1 3.0 3 ★ Chiu,Chih-Chou GBM 17 0 須修過資料探勘與商業智慧乙課方得修習

Year-Semester	Course Number	Course Name	Phase	Credits	Hours	Required/Elective	Instructor	Class	Student NO.	Withdraw	Note
Spring Semester Year 2026	356639	Deep Learning and Business Forecasting	1	3.0	3	★	Chiu,Chih-Chou	GBM	17	0	須修過資料探勘與商業智慧乙課方得修習

Course Plan：

Instructor Chiu,Chih-Chou　Office Hours

Email chih3c@ntut.edu.tw

Last Updated 2026-01-08 11:51:27

Course Objective 本課程將介紹基於神經網路的深度學習技術及其在商情預測上之應用，主要內容包括：（1）深度學習和神經網路的基本概念和演算法；（2）深度學習的主流結構、啟動函數及正則化技術；（3）電腦視覺與自然語言處理技術應用案例；（4）深度學習主流結構的商情預測應用。通過課程的學習，同學們可瞭解神經網路基本概念；掌握深度學習中主要網路結構的基本概念和相關演算法；瞭解具體應用領域的背景知識；應用相關深度學習技術於商情預測。 This course will give a full picture of deep learning techniques and its application in business forecasting. Content includes: (1) basic concepts and algorithms of deep learning and neural networks; (2) popular network structures, activation functions, and regularization techniques; (3) principle and applications of computer vision and natural language processing. (4) applications of popular network structures in business forecasting. By learning this course, students will consolidate the basic concepts of neural networks; master the basic concepts and related algorithms of the main network structure in deep learning; understand the background knowledge of deep learning techniques with specific application fields; and understanding how to apply the main network structure in business forecasting.

Course Schedule 1(02/24) 課程簡介 2(03/03) Google Colab 安裝/Python語法 3(03/10) MLP神經網路概念與訓練 4(03/17) MLP商情預測案例 Assignment 1 5(03/24) 卷積神經網路(CNN)1 6(03/31) 卷積神經網路(CNN)2 7(04/07) CNN商情預測案例 Assignment 2 8(04/14) 循環神經網路(RNN)1 9(04/21) 循環神經網路(RNN)2 10(04/28) RNN商情預測案例 Assignment 3 11(05/05) Midterm 12(05/12) 長短時記憶網(LSTM) 13(05/19) LSTM商情預測案例 Assignment 4 14(05/26) 自然語言處理案例 Assignment 5 15(06/02) 論文閱讀與討論1 16(06/09) 論文閱讀與討論2 17(06/16) 期末報告 18(06/23) 期末考

Evaluation and grading policy Midterm/Final Exam 25%/25% Project & Presentation 25% Assignments 25%

Materials All right reserved. Do not reproduce without permission.

Foreign-language textbooks:No
 Christopher Bishop. Pattern Recognition and Machine Learning. Springer Press.  Li Deng and Dong Yu. Deep Learning Methods and Applications. Now Publisher. http://research.microsoft.com/pubs/219984/BOOK2014.pdf  Yoshua Bengio. Learning Deep Architectures for AI. Now Publisher.  Ian Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning. MIT Press. http://www.deeplearningbook.org/  周志華《機器學習》清華大學出版社，2016.

The access to curricular consultation 課程諮詢管道
1. Office hour 詢問
2. Google meet 遠距討論
3. Line group 群組訊息分享及討論

Expanding teaching and resources

The course corresponds to the SDGs SDG3：良好健康和福祉（Good Health and Well-being）
SDG9：產業創新與基礎設施（Industry, Innovation and Infrastructure）

Does the course incorporate AI ● 使用生成式AI作為教學過程的輔助工具（Use generative AI tools as an aid to the teaching process）

Note
　

Instructor	Chiu,Chih-Chou　Office Hours
Email	chih3c@ntut.edu.tw
Last Updated	2026-01-08 11:51:27
Course Objective	本課程將介紹基於神經網路的深度學習技術及其在商情預測上之應用，主要內容包括：（1）深度學習和神經網路的基本概念和演算法；（2）深度學習的主流結構、啟動函數及正則化技術；（3）電腦視覺與自然語言處理技術應用案例；（4）深度學習主流結構的商情預測應用。通過課程的學習，同學們可瞭解神經網路基本概念；掌握深度學習中主要網路結構的基本概念和相關演算法；瞭解具體應用領域的背景知識；應用相關深度學習技術於商情預測。 This course will give a full picture of deep learning techniques and its application in business forecasting. Content includes: (1) basic concepts and algorithms of deep learning and neural networks; (2) popular network structures, activation functions, and regularization techniques; (3) principle and applications of computer vision and natural language processing. (4) applications of popular network structures in business forecasting. By learning this course, students will consolidate the basic concepts of neural networks; master the basic concepts and related algorithms of the main network structure in deep learning; understand the background knowledge of deep learning techniques with specific application fields; and understanding how to apply the main network structure in business forecasting.
Course Schedule	1(02/24) 課程簡介 2(03/03) Google Colab 安裝/Python語法 3(03/10) MLP神經網路概念與訓練 4(03/17) MLP商情預測案例 Assignment 1 5(03/24) 卷積神經網路(CNN)1 6(03/31) 卷積神經網路(CNN)2 7(04/07) CNN商情預測案例 Assignment 2 8(04/14) 循環神經網路(RNN)1 9(04/21) 循環神經網路(RNN)2 10(04/28) RNN商情預測案例 Assignment 3 11(05/05) Midterm 12(05/12) 長短時記憶網(LSTM) 13(05/19) LSTM商情預測案例 Assignment 4 14(05/26) 自然語言處理案例 Assignment 5 15(06/02) 論文閱讀與討論1 16(06/09) 論文閱讀與討論2 17(06/16) 期末報告 18(06/23) 期末考
Evaluation and grading policy	Midterm/Final Exam 25%/25% Project & Presentation 25% Assignments 25%
Materials	All right reserved. Do not reproduce without permission. Foreign-language textbooks:No  Christopher Bishop. Pattern Recognition and Machine Learning. Springer Press.  Li Deng and Dong Yu. Deep Learning Methods and Applications. Now Publisher. http://research.microsoft.com/pubs/219984/BOOK2014.pdf  Yoshua Bengio. Learning Deep Architectures for AI. Now Publisher.  Ian Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning. MIT Press. http://www.deeplearningbook.org/  周志華《機器學習》清華大學出版社，2016.
The access to curricular consultation	課程諮詢管道 1. Office hour 詢問 2. Google meet 遠距討論 3. Line group 群組訊息分享及討論
Expanding teaching and resources
The course corresponds to the SDGs	SDG3：良好健康和福祉（Good Health and Well-being） SDG9：產業創新與基礎設施（Industry, Innovation and Infrastructure）
Does the course incorporate AI	● 使用生成式AI作為教學過程的輔助工具（Use generative AI tools as an aid to the teaching process）
Note