Course Syllabus

Course Information：

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

Spring Semester
Year 2019 259430 Machine Learning 1 3.0 3 ★ SHINGCHERN YOU GCSIE
IEECSG 21 8 四資四、資工所與電資外生所合開、限20人

Year-Semester	Course Number	Course Name	Phase	Credits	Hours	Required/Elective	Instructor	Class	Student NO.	Withdraw	Note
Spring Semester Year 2019	259430	Machine Learning	1	3.0	3	★	SHINGCHERN YOU	GCSIE IEECSG	21	8	四資四、資工所與電資外生所合開、限20人

Course Plan：

Instructor SHINGCHERN YOU

Email scyou@ntut.edu.tw

Last Updated 2019-03-04 18:32:31

Course Objective This course covers a broad classes of machine learning algorithms to be able to conduct research in this field after completing this course. 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 progress field.

Course Schedule Week 1: Class announcement and introduction to machine learning (CH 1) Week 2: Holiday Week 3: Basics of spervised learning (Example: K NN), VC dimension, and regression (CH 2). Baysian decision theory (CH 3) and Naive Bayes classifiers (CH 5) Week 4: ML and MAP estimation; Bias vs variance dilemma (CH 4). Sample mean mean and sample covariance (CH 5). Dimension reduction techniques: PCA, FA (CH 6) Week 5: Dimension reduction techniques: LDA and ICA. Clustering algorithm: k-mean (CH 7) Week 6: Unsupervised neural networks (CH 12): Competitive learning, SOFM, and ART. Decision trees: ID3, C4.5, and random forest (CH 8) Week 7: Holiday Week 8: Decision trees (continued). Mixer model: GMM and EM algorithm (CH 7) Week 9: Genetic algorithms. Basics of optiminization. Week 10: MT Week 11: MT sol. Gradient search and linear discrimination (CH 10) Week 12: Feedforward neural networks with examples: radical basis networks and multi-layer perceptrons. Back propagation and regularization methods (CH 11) Week 13: Deep learning and convolutional neural networks Week 14: More on deep neural networks: Autoencoder, LSTM, and others Week 15: SVM (CH 13) and HMM (CH 15) Week 16: Combining multiple classifiers (CH 17) Week 17: Design and analysis of experiments (CH 19) & Reinforcement learning (CH 18) 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:Yes
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

Note
　

Instructor	SHINGCHERN YOU
Email	scyou@ntut.edu.tw
Last Updated	2019-03-04 18:32:31
Course Objective	This course covers a broad classes of machine learning algorithms to be able to conduct research in this field after completing this course. 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 progress field.
Course Schedule	Week 1: Class announcement and introduction to machine learning (CH 1) Week 2: Holiday Week 3: Basics of spervised learning (Example: K NN), VC dimension, and regression (CH 2). Baysian decision theory (CH 3) and Naive Bayes classifiers (CH 5) Week 4: ML and MAP estimation; Bias vs variance dilemma (CH 4). Sample mean mean and sample covariance (CH 5). Dimension reduction techniques: PCA, FA (CH 6) Week 5: Dimension reduction techniques: LDA and ICA. Clustering algorithm: k-mean (CH 7) Week 6: Unsupervised neural networks (CH 12): Competitive learning, SOFM, and ART. Decision trees: ID3, C4.5, and random forest (CH 8) Week 7: Holiday Week 8: Decision trees (continued). Mixer model: GMM and EM algorithm (CH 7) Week 9: Genetic algorithms. Basics of optiminization. Week 10: MT Week 11: MT sol. Gradient search and linear discrimination (CH 10) Week 12: Feedforward neural networks with examples: radical basis networks and multi-layer perceptrons. Back propagation and regularization methods (CH 11) Week 13: Deep learning and convolutional neural networks Week 14: More on deep neural networks: Autoencoder, LSTM, and others Week 15: SVM (CH 13) and HMM (CH 15) Week 16: Combining multiple classifiers (CH 17) Week 17: Design and analysis of experiments (CH 19) & Reinforcement learning (CH 18) 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:Yes 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
Note