ESM5205: Learning from Big Data (Fall 2021)
Final Scores --> [here]
Overview
This course provides an elementary introduction to modern techniques for learning from big data. Students will learn the theories and applications of machine learning and deep learning, including feed-forward neural networks, convolutional neural networks, recurrent neural networks, graph neural networks, autoencoders, and deep generative models.
* This course is equivalent to "ESM5120: Learning from Data". Do not sign up if already taken.
** Prerequisites: Linear Algebra, Applied Statistics I & II, Data Mining (or equivalent)
*** You must have taken the prerequisite course (or equivalent) before taking this course.
General Information
Class Time: Mon 15:00~18:00
Location: online – icampus (https://icampus.skku.edu/)
Language: English (except Q&A)
Instructor
Prof. Seokho Kang
Office: 27408B (Engineering Building 2)
E-mail: s.kang@skku.edu
Office Hours: by appointment via e-mail
Teaching Assistant
Mr. Jongmin Han and Mr. Eugene Yang
Office: 27407 - Data Mining Lab. (Engineering Building 2)
E-mail: hjm9702@gmail.com and cneyang@g.skku.edu
References
Ian Goodfellow, Yoshua Bengio & Aaron Courville, Deep Learning, MIT Press, 2016. (https://www.deeplearningbook.org/ )
Trevor Hastie, Robert Tibshirani & Jerome Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd ed.), Springer, 2009. (https://web.stanford.edu/~hastie/ElemStatLearn/)
https://github.com/ChristosChristofidis/awesome-deep-learning
Evaluation
Attendance (10%)
Assignments (10%)
Presentation (10%)
Mid-term Exam (30%)
Final Exam (40%)
Total (100% + a)
Schedule (Subject to Change)
Syllabus [download]
Note: ALL classes will be conducted online using icampus.
Lecture Notes
[8/30] Course Introduction [download]
[9/6] 1. Machine Learning Basics [download]
[9/13] 2. Deep Neural Networks [download]
[9/20] 3. Optimization [download]
[9/27] 4. Regularization [download]
[10/4] 5. Practical Methology [download]
[10/11] Review Session (Lectures 1-5, in Korean, optional)
[10/18] Mid-Term Exam (online, icampus)
[11/22] Special Topics in Deep Learning - Invited Talk by Myeonginn Kang (Ph.D. Student, SKKU)
[11/29] Review Session (Lectures 6-10, in Korean, optional)
[12/6] Final Exam (online, icampus)
Supplementary Materials
Presentation
Each student will give a 10-min presentation in class (in English). The objective is to share the applications of deep learning in students’ own research fields. Students are required to schedule the presentation (the schedule form has been released on icampus). The presentation topic should be relevant to the lecture topic of the same day. The presentation video and material should be submitted to the instructor via e-mail at least one day before the presentation.
Assignments
All assignments should be submitted to icampus by midnight of the due date. Late submissions will NOT be accepted.
[A1] Self-introduction report (due date: 9/13)
[A2] Research proposal (due date: 11/29)
Academic Integrity
Students are responsible for maintaining high standards of academic integrity in all of their class activities. Cheating or plagiarism in any form will not be tolerated. Any violation of academic integrity is a serious offense and is therefore subject to an appropriate sanction or penalty.