查詢教學大綱與進度

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

108-2 270958 機器學習 1 3.0 3 ★ 尤信程資工所
電資外生所 22 3 四資四、資工所和IEECS合開、上限20人電外10人

學年期	課號	課程名稱	階段	學分	時數	修	教師	班級	人	撤	備註
108-2	270958	機器學習	1	3.0	3	★	尤信程	資工所電資外生所	22	3	四資四、資工所和IEECS合開、上限20人電外10人

教學大綱與進度：

教師姓名尤信程

Email scyou@ntut.edu.tw

最後更新時間 2019-12-17 08:25:15

課程大綱 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 schedule field.

課程進度 Week 1: Class announcement and introduction to machine learning (CH 1) Week 2: Holiday Week 3: Basics of supervised learning (Example: k-NN), VC dimension, and regression (CH 2). Bayesian 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: Basics of optimization. Week 9: MT Week 10: MT sol. Gradient search and linear discrimination (CH 10) Week 11: Feedforward neural networks with examples: radical basis networks and multi-layer perceptrons. Back propagation and regularization methods (CH 11) Week 12: Deep learning and convolutional neural networks Week 13: More on deep neural networks: YOLO, Autoencoder, LSTM, and others Week 14: SVM (CH 13) Week 15: Combining multiple classifiers (CH 17) & Design and analysis of experiments (CH 19) Week 16: Reinforcement learning (Basics, Q learning, DQN) Week 17: Reinforcement learning (policy-based learning & PPO) Week 18: Final exam

評量方式與標準 MT 30 % Final 40 % HW 30 % Project 10 % (optional)

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：是
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.

課程諮詢管道

備註

教師姓名	尤信程
Email	scyou@ntut.edu.tw
最後更新時間	2019-12-17 08:25:15
課程大綱	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 schedule field.
課程進度	Week 1: Class announcement and introduction to machine learning (CH 1) Week 2: Holiday Week 3: Basics of supervised learning (Example: k-NN), VC dimension, and regression (CH 2). Bayesian 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: Basics of optimization. Week 9: MT Week 10: MT sol. Gradient search and linear discrimination (CH 10) Week 11: Feedforward neural networks with examples: radical basis networks and multi-layer perceptrons. Back propagation and regularization methods (CH 11) Week 12: Deep learning and convolutional neural networks Week 13: More on deep neural networks: YOLO, Autoencoder, LSTM, and others Week 14: SVM (CH 13) Week 15: Combining multiple classifiers (CH 17) & Design and analysis of experiments (CH 19) Week 16: Reinforcement learning (Basics, Q learning, DQN) Week 17: Reinforcement learning (policy-based learning & PPO) Week 18: Final exam
評量方式與標準	MT 30 % Final 40 % HW 30 % Project 10 % (optional)
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：是 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.
課程諮詢管道
備註