課程名稱 |
機器學習 Machine Learning |
開課學期 |
112-1 |
授課對象 |
生醫電子與資訊學研究所 |
授課教師 |
劉子毓 |
課號 |
EE5184 |
課程識別碼 |
921EU2620 |
班次 |
01 |
學分 |
4.0 |
全/半年 |
半年 |
必/選修 |
選修 |
上課時間 |
星期三2,3,4,5(9:10~13:10) |
上課地點 |
電二229 |
備註 |
本課程以英語授課。 總人數上限:90人 外系人數限制:20人 |
|
|
課程簡介影片 |
|
核心能力關聯 |
核心能力與課程規劃關聯圖 |
課程大綱
|
為確保您我的權利,請尊重智慧財產權及不得非法影印
|
課程概述 |
The machine learning course is a comprehensive program designed to engage in data-driven decision-making. Throughout the course, students will learn to understand the fundamental principles and techniques that underpin modern machine learning. We will explore topics such as supervised and unsupervised learning, Bayesian and non-Bayesian approaches. The curriculum also includes hands-on practical exercises, enabling students to develop a strong foundation in data preprocessing, model selection, and evaluation on real-world applications. By the end of the course, participants emerge with a profound understanding of machine learning algorithms, the ability to implement them, and the confidence to harness the power of data to drive innovation and insights in various domains. |
課程目標 |
- Explain the mathematics behind the Machine Learning models.
- Implement Machine Learning methods and apply them to real applications
- Analyze and critique the numerical results
|
課程要求 |
Language: This course will be offered in English, including the homeworks and exams. However, students can ask questions in the language they feel most comfortable.
Class arrangement: This is a 4-credit course, taking place every Wednesday 9:10 am - 13:10 pm.The first 3 hours (9:10 am - 12:10 pm) will be the lectures. The last hour (12:20-13:10) will be the TA session.
|
預期每週課後學習時數 |
4-5 hours per week of studies and homework after class. |
Office Hours |
每週五 09:00~10:00 |
指定閱讀 |
NA. |
參考書目 |
- James, Gareth, et al. An introduction to statistical learning. Vol. 112. New York: springer, 2013.
- Zhang, Aston, et al. "Dive into deep learning." arXiv preprint arXiv:2106.11342 (2021).
- Blum, Avrim, John Hopcroft, and Ravindran Kannan. Foundations of data science. Cambridge University Press, 2020.
- Shalev-Shwartz, Shai, and Shai Ben-David. Understanding machine learning: From theory to algorithms. Cambridge university press, 2014.
- Murphy, Kevin P. Probabilistic machine learning: an introduction. MIT press, 2022.
- Akkus, Cem, et al. "Multimodal Deep Learning." arXiv preprint arXiv:2301.04856 (2023).
- Sutton, Richard S., and Andrew G. Barto. Reinforcement learning: An introduction. MIT press, 2018. |
評量方式 (僅供參考) |
No. |
項目 |
百分比 |
說明 |
1. |
Midterm |
30% |
|
2. |
Final exam |
30% |
|
3. |
Homework |
40% |
The assignments include take-home quizzes implementation on colab. |
|
針對學生困難提供學生調整方式 |
上課形式 |
以錄音輔助 |
作業繳交方式 |
|
考試形式 |
|
其他 |
由師生雙方議定 |
|
週次 |
日期 |
單元主題 |
第1週 |
9/06 |
Introduction and rubric review; What is AI? What is ML? |
第2週 |
9/13 |
Regression; Cross validation; Hyperparameter optimization |
第3週 |
9/20 |
Support vector machine (SVM); the kernel trick |
第4週 |
9/27 |
Decision tree, naive Bayes classifier |
第5週 |
10/04 |
Ensemble methods, random forest and AdaBoost |
第6週 |
10/11 |
Dimension reduction, PCA, MDS, tSNE |
第7週 |
10/18 |
GMM as an example of Bayesian modeling |
第8週 |
10/25 |
Midterm |
第9週 |
11/01 |
Multi layer perceptron (MLP) |
第10週 |
11/08 |
Convolutional neural network (CNN) |
第11週 |
11/15 |
Autoencoder |
第12週 |
11/22 |
Variational aucoencoder (VAE) |
第13週 |
11/29 |
Generative adversarial network (GAN) |
第14週 |
12/06 |
Transformer |
第15週 |
12/13 |
Guest lecture |
第16週 |
12/20 |
Final exam |
|