Course Syllabus

Course Information：

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

Spring Semester
Year 2023 316604 Machine Learning 1 3.0 3 ★ SHINGCHERN YOU GCSIE
IEECSG 34 4 資工所和電資外生所合開

Year-Semester	Course Number	Course Name	Phase	Credits	Hours	Required/Elective	Instructor	Class	Student NO.	Withdraw	Note
Spring Semester Year 2023	316604	Machine Learning	1	3.0	3	★	SHINGCHERN YOU	GCSIE IEECSG	34	4	資工所和電資外生所合開

Course Plan：

Instructor SHINGCHERN YOU　Office Hours

Email scyou@ntut.edu.tw

Last Updated 2022-12-16 13:38:18

Course Objective This course covers a broad classes of machine learning algorithms. After taking this course, students should be able to conduct research in this field. The emphasis of this course is not in the theoretical development (math), but in the understanding level. Therefore, many examples will be given in the lecture to show how to apply the equations to real problems. The detailed contents are given in the course schedule field. Prerequisite: Calculus (partial derivatives), undergrad linear algebra (eigenvalues & eigenvectors), undergrad probability (random variable, joint density, Gaussian distribution), and programming skills (Python)

Course Schedule Week 1: Class announcement and introduction to machine learning Week 2: Holiday & introduction to machine learning Week 3: Basics of supervised learning (classification and regression), VC dimension, Bayesian decision theory, and Naive Bayes classifiers Week 4: ML and MAP estimation, Sample mean and sample covariance, multivariate Gaussian, Bias vs variance dilemma, Dimension reduction techniques: PCA, FA Week 5: Dimension reduction techniques: LDA and ICA, Unsupervised learning: Clustering algorithm (k-means) Week 6: Decision trees: ID3, C4.5, and bagging algorithm (random forest) Week 7: Holiday Week 8: Basics of optimization Week 9: MT Week 10: MT sol. Gradient search and linear discrimination Week 11: Feedforward neural networks with examples: multi-layer perceptrons, Back propagation, and Regularization methods Week 12: Deep learning and convolutional neural networks Week 13, 14: More on deep neural networks: YOLO, Autoencoder, LSTM, and advanced topics, such as Bayesian networks, confidence of classification, and self-supervised learning (if time permitted) Week 15: SVM Week 16: Adaboost and Ensemble learning Week 17: Design and analysis of experiments Week 18: Final exam

Evaluation and grading policy MT 30 % Final 40 % HW 30 % Project 10 % (optional)

Materials All right reserved. Do not reproduce without permission.

Foreign-language textbooks:No
Reference text book: Introduction to machine learning. E. Alpaydin. 2nd ed or 3rd ed. Note: textbook is only used to follow the presentation order. Much of the detailed lecture materials are NOT covered in the textbook.

The access to curricular consultation Office: Tech building 1533
Email: scyou@ntut.edu.tw

The course corresponds to the SDGs

Note
In case online lecturing is required by CDC, we will use the Microsoft Teams as the lecturing platform (NTUT-Sync]110-2_298550_機器學習). E-mail me if you have any problems: scyou@ntut.edu.tw

Instructor	SHINGCHERN YOU　Office Hours
Email	scyou@ntut.edu.tw
Last Updated	2022-12-16 13:38:18
Course Objective	This course covers a broad classes of machine learning algorithms. After taking this course, students should be able to conduct research in this field. The emphasis of this course is not in the theoretical development (math), but in the understanding level. Therefore, many examples will be given in the lecture to show how to apply the equations to real problems. The detailed contents are given in the course schedule field. Prerequisite: Calculus (partial derivatives), undergrad linear algebra (eigenvalues & eigenvectors), undergrad probability (random variable, joint density, Gaussian distribution), and programming skills (Python)
Course Schedule	Week 1: Class announcement and introduction to machine learning Week 2: Holiday & introduction to machine learning Week 3: Basics of supervised learning (classification and regression), VC dimension, Bayesian decision theory, and Naive Bayes classifiers Week 4: ML and MAP estimation, Sample mean and sample covariance, multivariate Gaussian, Bias vs variance dilemma, Dimension reduction techniques: PCA, FA Week 5: Dimension reduction techniques: LDA and ICA, Unsupervised learning: Clustering algorithm (k-means) Week 6: Decision trees: ID3, C4.5, and bagging algorithm (random forest) Week 7: Holiday Week 8: Basics of optimization Week 9: MT Week 10: MT sol. Gradient search and linear discrimination Week 11: Feedforward neural networks with examples: multi-layer perceptrons, Back propagation, and Regularization methods Week 12: Deep learning and convolutional neural networks Week 13, 14: More on deep neural networks: YOLO, Autoencoder, LSTM, and advanced topics, such as Bayesian networks, confidence of classification, and self-supervised learning (if time permitted) Week 15: SVM Week 16: Adaboost and Ensemble learning Week 17: Design and analysis of experiments Week 18: Final exam
Evaluation and grading policy	MT 30 % Final 40 % HW 30 % Project 10 % (optional)
Materials	All right reserved. Do not reproduce without permission. Foreign-language textbooks:No Reference text book: Introduction to machine learning. E. Alpaydin. 2nd ed or 3rd ed. Note: textbook is only used to follow the presentation order. Much of the detailed lecture materials are NOT covered in the textbook.
The access to curricular consultation	Office: Tech building 1533 Email: scyou@ntut.edu.tw
The course corresponds to the SDGs
Note	In case online lecturing is required by CDC, we will use the Microsoft Teams as the lecturing platform (NTUT-Sync]110-2_298550_機器學習). E-mail me if you have any problems: scyou@ntut.edu.tw