CE6143 - Introduction to Data Science (Fall 2025)

Lecture language: English

Meeting time

Location

Staff

Recommended textbooks

Supplementary materials

Grading

Slides

Progress (subject to change)

WeekDateContentExercise
19/21. Overview of the course
29/91. Introduction to ML
2. KNN
3. k-means
4. Distance measures
Project proposal (group) (due: 9/15 23:59:59)
39/161. Entropy
2. Decision tree
49/231. Matrix derivatives
2. Linear regression and regularization (Lasso, Ridge, Elastic-net)
59/30Logistic regression and gradient ascent
610/71. Evaluation metrics for binary classification, multi-class classification, and multi-label classification
2. ROC curve vs PR curve
710/141. Entropy, cross-entropy, and KL-divergence
2. Practical concerns on traditional machine learning
3. Ensemble learning
810/211. Gradient boosting machines
2. Linear SVM
1. Progress report (due: 10/20 23:59:59)
2. Kaggle Competition begins (due: 11/10 23:59:59)
910/28Multi-layer perceptron and backpropgagation
1011/4Convolutional neural network
1111/11
No physical class; lecture is given by recorded video
1. Kernel SVM
2. Regularized linear regression and classification
3. Linear SVM with poly-2 terms vs. polynomial kernel SVM
1211/181. Recurrent neural network
2. Practical concerns of DNN
1311/251. Word2Vec
2. Transformer and Large Language Model
Mini-ml implementation and report (due: 11/24 23:59:59)
1412/2Attend AI Sustainability Forum (AI永續論壇)
1512/91. LoRA: low-rank adaptation
2. MoE: mixture of experts
3. Associated learning
4. Constrastive learning, supervised contrastive learning and SCPL
1612/16Diffusion modelFinal project (due: 12/15 23:59:59)