機器學習

Course description This introductory course covers fundamental concepts, techniques, and algorithms in machine learning, beginning with overviews in topics such as linear regression, classification, unsupervised learning, as well as introduction of deep learning. The course will guide students to understand the basic ideas and insights behind the design of advanced machine learning algorithms as well as some rationale of why a model works well and how to use a model properly. Learning Objectives 1. Understand what machine can learn from data and the basic learning strategies. 2. Be able to formulate machine learning problems corresponding to the application contexts. 3. Understand a variety of machine learning algorithms and their pros and cons. 4. Have a basic theoretical knowledge of machine learning approaches. 5. Be able to apply machine learning algorithms to solve problems. 6. Be capable of performing experiments in machine learning using real-world data.

Linear Algebra, Differential Equations, Probability and Statistics.

Quizzes: 10% Assignments: 40% Competition: 20% Final project: 20% Participation: 10%

References (optional): Witten, I. H., Frank, E., Hall, M. A., & Pal, C. J. (2016). Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann. Abu-Mostafa, Y. S., Magdon-Ismail, M., & Lin, H. T. (2012). "Learning from data" (Vol. 4). New York, NY, USA:: AMLBook. Bishop, C. M. (2006). "Pattern recognition and machine learning". springer.

地點

Chun-Shu Wei: HA323 蔡旻均: TBD 黃大祐: TBD

時間

by appointment

聯絡方式

Chun-Shu Wei: cwei@nctu.edu.tw 蔡旻均: dollars9256741@gmail.com 黃大祐: d86518.ms04@g2.nctu.edu.tw