Public repository for lecture notes / labs, etc
- Semester: Fall 2025
- Instructor: Tao LIN
- Time and Location:
- Theory: Tuesday 13:30 - 14:15, 14:20 - 15:05, 15:10 - 15:55, YunGu campus E13-204
- Exercise: Thursday 08:00 - 09:35, YunGu campus E13-204
- Canvas
See course_info_sheet for more details.
| Date | Session | Class Hour | Instructor | Theme / Topic | Teaching Activities (Lecture/Practical) |
|---|---|---|---|---|---|
| Sep. 02 | Foundations of Data Science | Tao Lin | Course logistics; Introduction to ML (why ML, and why now); Linear algebra review; Probability review | Lecture | |
| Sep. 04 | Foundations of Data Science | TA | Lab 1 (graded): mathematical foundations | Practical | |
| Sep. 09 | Linear Models for Regression | Tao Lin | Linear regression; Cost functions; Introduction to optimization | Lecture | |
| Sep. 11 | Linear Models for Regression | TA | Lab 2: Introduction to Python, NumPy, and PyTorch; Lab 1 due; Project 1 release | Practical | |
| Sep. 16 | Linear Models for Regression | Tao Lin | Least squares; Probabilistic interpretation: Maximum Likelihood Estimation (MLE); Over- and under-fitting; Ridge regression; Lasso | Lecture | |
| Sep. 18 | Linear Models for Regression | TA | Lab 3 | Practical | |
| Sep. 23 | Generalization, and Model Selection | Tao Lin | Generalization; Bias-Variance decomposition; Double descent phenomenon; Model selection, and validation | Lecture | |
| Sep. 25 | Generalization, and Model Selection | TA | Lab 4 (graded) | Practical | |
| Sep. 30 | Linear Models for Classification | Tao Lin | Classification; Logistic regression; Logistic regression and its optimization (MLE, Steepest descent, Newton's method, etc.) | Lecture | |
| Oct. 09 | Linear Models for Classification | TA | Lab 5; Lab 4 due | Practical | |
| Oct. 14 | Generalized Linear Models | Tao Lin | Exponential family; Generalized linear models | Lecture | |
| Oct. 16 | Generalized Linear Models | TA | QA for Project 1; | Practical | |
| Oct. 21 | Generative Learning Algorithms | Tao Lin | Discriminative vs. Generative learning algorithms; Gaussian Discriminant Analysis (GDA); GDA and Linear Discriminant Analysis (LDA); GDA and Naïve Bayes; GDA vs. Logistic regression | Lecture | |
| Oct. 23 | Generative Learning Algorithms | TA | QA for Project 1; Project 1 due; Project 2 release | Practical | |
| Oct. 28 | Nonparametric Methods | Tao Lin | Parametric vs. nonparametric models; K-nearest neighbors; Decision trees; Bagging and random forest | Lecture | |
| Oct. 30 | Nonparametric Methods | TA | Lab 6 (graded) | Practical | |
| Nov. 04 | Kernel Methods, SVM | Tao Lin | Kernel methods; Support Vector Machine (SVM) | Lecture | |
| Nov. 06 | Kernel Methods, SVM | TA | Lab 7; Lab 6 due; | Practical | |
| Nov. 11 | Mixture Models, EM Algorithm | Tao Lin | Introduction to unsupervised Learning; Clustering; K-means; Gaussian Mixture Model (GMM); EM algorithm | Lecture | |
| Nov. 13 | Mixture Models, EM Algorithm | TA | Lab 8 | Practical | |
| Nov. 18 | Neural Networks | Tao Lin | Neural Networks - basics, representation power; Neural Networks – back-propagation | Lecture | |
| Nov. 20 | Neural Networks | TA | Lab 9 | Practical | |
| Nov. 25 | Deep Neural Networks | Tao Lin | Deep Neural Networks – advanced architectures (CNN, RNN, Transformer, etc.) | Lecture | |
| Nov. 27 | Deep Neural Networks | TA | Lab 10 (graded) | Practical | |
| Dec. 02 | Deep Neural Networks | Tao Lin | Deep Neural Networks – optimization | Lecture | |
| Dec. 04 | Deep Neural Networks | TA | Lab 11 (graded) | Practical | |
| Dec. 09 | Deep Neural Networks | Tao Lin | Beyond supervised learning: - zero/few shot learning | Lecture | |
| Dec. 11 | Deep Neural Networks | TA | Lab 11 (due) | Practical | |
| Dec. 16 | Deep Neural Networks | Tao Lin | Self-supervised Learning; LLMs | Lecture | |
| Dec. 18 | TA | Lab 12; QA for Project 2 | Practical | ||
| Dec. 23 | Recitation | Tao Lin | Course recitation | Lecture | |
| Dec. 25 | TA | QA for Project 2; Project 2 due | Practical |
