2025 spring

기계학습 / Machine Learning (2 Div)

This course covers theoretical backgrounds and practical implementation of different machine learning techniques, including supervised learning, unsupervised learning, deep learning, active learning, anmd reinforcement learning. In addition, it explores the entire pipeline to build applications of machine learning with practices. Furthermore, it provides a broad introduction to ethical issues relevant to machine learning.

Instruction

Course Staff
Time & Location
  • Tue./Wed. 09:00 - 10:45, #608, College of Engineering #6
Office Hours
  • Tue. 13:00 - 15:00
Textbook
  • Primary
    • [Ge23] Aurélien Géron. 2023. Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, 3rd Ed. O`Reilly
  • Secondary
    • [Oh21] 오일석. 2021. 기계 학습. 한빛 아카데미
    • [Ow22] Louis Owen. 2022. Hyperparameter Tuning with Python: Boost your machine learning model’s performance via hyperparameter tuning. Packt.
    • [Br20] Jason Brownlee. 2020. Data Preparation for Machine Learning, 1.1 Ed. Machine Learning Mastery
    • [Br21] Jason Brownlee. 2021. Imbalanced Classification with Python, 1.3 Ed. Machine Learning Mastery
    • [Mo24] Christoph Molnar. 2024. Interpretable Machine Learning
    • [Ma23] Serg Masis. Interpretable Machine Learning with Python. 2023
Prerequisite
  • (Mandatory) Python Programming, Data Analysis Programming
    • All materials were prepared assuming students were proficient in Python programming and familiar with Numpy and Pandas.
Grading Policy
Data Collection (10%)
  • Collect sensor data for human activity recognition
Individual ML Competitions via Kaggle (80%)
  • Round 0 - Being Familiar with Kaggle (5%)
  • Round 1 - TBD (9%)
  • Round 2 - TBD (9%)
  • Round 3 - TBD (9%)
  • Special Round - TBD (15%)
  • Round 4 - TBD (9%)
  • Round 5 - TBD (9%)
  • Final Round - Human Activity Recognition (15%)
Attendance (10%)
  • 1% of credit is deducted for each absence
  • 3-Lateness = 1-Absence
  • 11-Absence = F grade

Schedule

Week 01
March 04: Overview & Logistics
March 05: Machine Learning Landscape
  • Lecture
  • Reference
    • [Ge23] Chap. 1
    • [Oh21] Chap. 1
Week 02
March 11: Machine Learning Pipeline
  • Lecture
  • Reference
    • [Ge23] Chap. 2
    • D. Sculley et al. 2015. Hidden technical debt in Machine learning systems. In Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2 (NIPS'15).
    • Soowon Kang et al. 2023. K-EmoPhone: A Mobile and Wearable Dataset with In-Situ Emotion, Stress, and Attention Labels. Sci Data 10, 351 (2023).
March 12: End-to-End Practice for Machine Learning Pipeline
  • Practice
  • Reference
    • [Ge23] Chap. 3
  • (Announce) Individual ML Competition Round 0: Getting Familiar w/ Kaggle
    • Due: March 18
Week 03
March 18: Linear Model
  • Lecture
  • Reference
    • [Ge23] Chap. 4
    • [Oh21] Chap. 2
March 19: Linear Model - Practice
  • Practice
  • Reference
    • [Ge23] Chap. 4
    • [Oh21] Chap. 2
  • (Announce) Individual ML Competition Round 1: Telemarketing
    • Due: March 31
Week 04
March 25: Performance Measures
March 26: Cross-Validation
Week 05
April 01: Support Vector Machine
April 02: Decision Tree
  • Lecture
  • Practice
  • Reference
    • [Ge23] Chap. 6
  • (Announce) Individual ML Competition Round 2
    • Due: April 14
Week 06
April 08: Ensemble Learning #1: Random Forest
April 09: Ensemble Learning #2: Gradient Boosting
Week 07
April 15: Imbalanced Classification
April 16: Feature Extraction
  • Lecture
  • Practice
  • Reference
    • Andreas Bulling et al. 2014. A tutorial on human activity recognition using body-worn inertial sensors. ACM Comput. Surv. 46, 3, Article 33.
    • Soujanya Poria et al. 2017. A review of affective computing: From unimodal analysis to multimodal fusion. Information Fusion, 37, 98–125.
  • (Announce) Individual ML Competition Midterm Round
    • Due: April 28
Week 08
April 22: Feature Selection
April 23: Focus on Midterm Exam
  • No Class
Week 09
April 29: Unsupervised Learning - Dimensionality Reduction
April 30: Unsupervised Learning - Novelty and Outlier Detection
  • Lecture
  • Practice
  • References
    • [Br20] Chap. 5
  • (Announce) Individual ML Competition Round 3
    • Due: May 12
Week 10
May 06: Substitution Holiday for Children's Day
  • No Class
May 07: Unsupervised Learning - Clustering
Week 11
May 13: Hyper-parameter Tuning #1
  • Lecture
  • Practice
  • Reference
    • [Ow22] Chap. 2, 3, 4, 7, 8
    • Tong Yu and Hong Zhu. 2000. Hyper-Parameter Optimization: A Review of Algorithms and Applications
May 14: Hyper-parameter Tuning #2
  • Lecture
  • Practice
  • Reference
    • [Ow22] Chap. 5, 6, 9, 10
    • Tong Yu and Hong Zhu. 2000. Hyper-Parameter Optimization: A Review of Algorithms and Applications
  • (Announce) Individual ML Competition Round 4
    • Due: May 26
Week 12
May 20: Artificial Neural Network
May 21: Deep Neural Network
Week 13
May 27: Convolution Neural Network
May 28: Recurrent Neural Network
  • Lecture
  • Practice
  • References
    • [Ge23] Chap. 15
    • [Oh21] Chap. 8
  • (Announce) Individual ML Competition Round 5
    • Due: June 09
  • (Announce) Data Collection Assignment: Sensor Data Collection
    • Due: June 09
Week 14
June 03: Substitution Holiday for Presidential Election
  • No class
June 04: Autoencoder
Week 15
June 10: Generative Models
June 11: Interpretability
  • Lecture
  • Practice
  • References
    • [Mo24] Chap. 5 - 10
    • [Ma23] Chap. 4 - 8
  • (Announce) Individual ML Competition Final Round
    • Due: June 22
Week 16
June 17: Focus on Final Assigment
  • No Class
June 23: Final Remark