2026 spring

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
    • [Fo23] David Foster. 2023. Generative Deep Learning: Teaching Machines to Paint, Write, Compose and Play, 2nd Ed. O`Reilly
    • [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
Prerequisite
  • 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 (15%)
  • Sensor data collection for human activity recognition
Individual ML Competitions via Kaggle (75%)
  • Round 0 – Being Familiar with Kaggle (5%)
  • Round 1 – TBA (11%)
  • Round 2 – TBA (11%)
  • Round 3 – TBA (11%)
  • Round 4 – TBA (11%)
  • Round 5 – TBA (11%)
  • Round 6 – 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 03 — Overview & Logistics
March 04 — Introduction: Machine Learning Landscape
Week 02
March 10 — Introduction: 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 11 — Introduction: End-to-End Practice
  • Practice
  • Reference
    • [Ge23] Chap. 3
  • (Announce) ML Competition Round 0: Getting Familiar w/ Kaggle
    • Due: March 18
Week 03
March 17 — Linear Model: Linear Regression
March 18 — Linear Model: Logistic Regression
Week 04
March 24 — Performance Estimation: Performance Measures
March 25 — Performance Estimation: Cross-Validation
  • Lecture
  • Practice
  • Reference
    • Berrar, D. 2019. Cross-Validation
  • (Announce) ML Competition Round 1
    • Due: April 08
Week 05
March 31 — Support Vector Machine
April 01 — Decision Tree
Week 06
April 07 — Ensemble Learning: Basics & Bagging
April 08 — Ensemble Learning: Boosting
  • Lecture
  • Practice
  • Reference
    • [Ge23] Chap. 7
  • (Announce) ML Competition Round 2
    • Due: April 22
Week 07
April 14 — Ensemble Learning: Gradient Boosted Trees
  • Lecture
  • Practice
  • Reference
    • [Ge23] Chap. 7
    • Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm SIGKDD international conference on knowledge discovery and data mining, 785-794
    • Guolin Ke et al. 2017. LightGBM: A highly efficient gradient boosting decision tree. Advances in neural information processing systems 30
    • Liudmila Prokhorenkova et al. 2018. CatBoost: unbiased boosting with categorical features. Advances in neural information processing systems 31
April 15 — Imbalanced Classification
Week 08
April 21 — Focus on Other Exams
  • No Class
April 22 — Feature Engineering: 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) ML Competition Round 3
    • Due: May 06
Week 09
April 28 — Feature Engineering: Feature Selection
April 29 — Unsupervised Learning: Dimensionality Reduction
Week 10
May 05 — Children's Day
  • No Class
May 06 — Unsupervised Learning: Clustering
  • Lecture
  • Practice
  • References
    • [Ge23] Chap. 9
  • (Announce) ML Competition Round 4
    • Due: May 20
  • (Announce) Data Collection Assignment: Sensor Data Collection
    • Due: May 20
Week 11
May 12 — Hyperparameter Tuning: Exhaustive Search & Heuristic Search
  • 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 13 — Hyperparameter Tuning: Bayesian Optimization & Multi-Fidelity Optimization
  • Lecture
  • Practice
  • Reference
    • [Ow22] Chap. 5, 6, 9, 10
    • Tong Yu and Hong Zhu. 2000. Hyper-Parameter Optimization: A Review of Algorithms and Applications
Week 12
May 19 — Deep Learning: Artificial Neural Network
May 20 — Deep Learning: Deep Neural Network
  • Lecture
  • Practice
  • References
    • [Ge23] Chap. 11
  • (Announce) ML Competition Round 5
    • Due: June 02
Week 13
May 26 — Deep Learning: Convolution Neural Network
May 27 — Deep Learning: Recurrent Neural Network
Week 14
June 02 — Generative Models: Autoencoder
  • Lecture
  • Practice
  • References
    • [Ge23] Chap. 17
  • (Announce) ML Competition Round 6
    • Due: June 17
June 03 — Substitution Holiday for Local Election
  • No class
Week 15
June 09 — Generative Models: Variational Autoencoder & Autoregressive Models
June 10 — Generative Models: Generative Adversarial Network
Week 16
June 16 — Generative Models: Diffusion Model
  • Lecture
  • References
    • [Fo23] Chap. 8
June 17: Final Remark