Machine Learning and Deep Learning for Data Science
(데이터사이언스를 위한 머신러닝 딥러닝)

Spring 2021

Tue/Thu, 09:30 - 10:45

Instructor: Dr. Wen-Syan Li (, Office: 942-412)
TA: Bui Tien Cuong (

Learning Objectives

By the end of this class, students will learn the main concepts, methodologies, and tools for machine learning and deep learning be able to recognize machine learning tasks in real-world problems develop the critical thinking to analyze a given task and perform model selection and evaluation. Students will also gain the experience of applying the data science process end-to-end as an individual and as a team member.


Part I. Machine Learning

1. Introduction of Machine Learning, family of algorithms, supervised learning, unsupervised learning, deep learning,

2. Linear Regression (Model Representation, Cost Function, Gradient Descent)

3. Linear Algebra Review / Linear Regression with Multiple Variables, Multiple Features

4. Linear Regression with Multiple Variables, Multiple Features, Some Useful Practices

5. Logistic Repression (classification, Hypothesis Representation, Decision Boundary, Cost Functions)

6. Logistic Repression (classification, Hypothesis Representation, Decision Boundary, Cost Functions) / Tools for Machine Learning

7. Regularization (overfitting,, underfitting, cost function, regularized regression algorithms)

8. Neural Network (Representation, learning, back propagation, reinforced learning, random initialization, etc.)

9. Neural Network (how to put everything together, examples, ) / Generic Algorithms

10. SVM / Clustering

11. Feature Reduction / Machine Learning System Design / Case study


Part II. Deep Learning

12. Deep Feedforward Networks / Regulation and Training for Deep Learning /

13. Convolutional Networks / Sequence Modeling / Practical Methodology / Applications/ Case Study


Part III. Deep Learning Research

14. Linear Factor Models / Autoencoders / Reprepresentional Learning / Monte Carlo Methods / etc.


Part IV. Project Presentation

15. Summary of the course and future research topics / project presentation


Familiarity with Python, R, or MATLAB is needed for programming-based assignments. A good reference is the Python Data Science Handbook by Jake VanderPlas. Students are encouraged to go through the book or on line before starting the class.


There is no single required textbook for this course as the lectures will be based on multiple textbooks, various articles, and web documents as well as real scenarios from external companies. Among numerous textbooks available in the market, the following are recommended.

1. Pattern Recognition and Machine Learning (Information Science and Statistics)by Christopher M. Bishop, ISBN-13:978-0387310732. On line material and downloadable pdf are available at

2. Machine Learning by Tom M Mitchell ISBN-13: 978-1259096952. On line material is available at

3. Deep Learning (Adaptive Computation and Machine Learning series) by Ian Goodfellow, Yoshua Bengio, Aaron Courville, ISBN-13:978-0262035613. On line material is available at

4. Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning series) second edition by Richard S. Sutton(Author), Andrew G. Barto, ISBN-13: 978-0262039246. On line material is available at (reinforcement learning focused book)

5. Machine Learning by Andrew Ng’s online machine learning course available at

Language Policy

This course will be taught in English. All lectures as well as exams and assignments will be given in English. Students will use English for answering exam questions and doing assignments.