2110743 Machine Learning (2/2025)

Zoom link:  https://chula.zoom.us/j/7474759219 

Shared Folder: https://drive.google.com/drive/folders/1bUEF_lbuAxB1KA1SgIXGmgHbVaVWVpEy?usp=sharing 

Schedule:

1. 11 Jan 2026: Course Introduction, Intro to Machine Learning (VDO Playlist, Slides from Tom Mitchell Textbook)

2. 18 Jan 2026: Concept Learning (Version Space, VDO Playlist, Slides from Tom Mitchell Textbook, Colab)

3. 25 Jan, 1 Feb 2026: Decision Tree Learning+XGBoosting (VDO Playlist, Slides from Tom Mitchell Textbook)

   • 1. Entropy (Colab)

     2. sklearn (Colab)

4. 8 Feb 2026: Neural Network(VDO Playlist ดูถึง More Area of Perceptrons, Slides from Tom Mitchell Textbook)

   • Random Forest (Colab)

5. 15, 22 Feb 2026: Neural Network(VDO Playlist ดูจนจบ Training a Perceptron, Slides from Tom Mitchell Textbook)

   • Perceptron Training Spreadsheet 

   • Perceptron Training Colab

   • Linear Node Training Spreadsheet

6. 1 Mar 2026: Midterm 

7. 8 Mar 26: Backpropagation Neural Network (VDO Playlist)

   • Colab for confusion matrix 

8. 15 Mar 26: Evaluating Hypothesis (VDO Clips,  Spreadsheet Link, Colab Link [ROC])

9. 22 Mar 26: SVM (VDO Clips, Colab, Book Chapter )

10. 5 Apr 26 CNN (VDO Clips) 

    • Pretrained CNN: colab

    • Transfer Learning: colab 

    • MNIST Keras: colab

    • LSTM (VDO Clips) 

11. 12 Apr 26: พักผ่อนนะครับ หยุดยาว ไม่เรียนครับ

12. 19 Apr 26: Antigravity Demonstration

13. 26 Apr 26: Naive Bayes Learning (VDO Clips), Colab Link of LSTM for Text Classification)

14. [Not in the 2025 class] Clustering (VDO Clips)

15. [Not in the 2025 class] Reinforcement Learning (VDO Clips)

16. 10 May 26 Final Exam (VDO Clip)

17. Project Presentation (YouTube VDO เท่านั้น)

    • Submitted via this form (Link), before 23:59 17 May 2026

    • 2-3 members/group 

    • Choose from 1: Supervised, 2: Unsupervised, 3: Insight from the class

      1. Supervised

         1. Choose 1 dataset 

         2. Apply 2-3 algorithms

         3. Fine tune model to be the best one 

      2. Unsupervised 

         1. Choose 1 dataset 

         2. Try to cluster data 

         3. Explain the result 

      3. Insight from the class 

         1. Choose one of sourcecodes from the class 

         2. Apply to new situation 

         3. Explain the result

Grading

1. Midterm 30% 

2. Final 40% 

3. Project (2-3 Students/group) 30%

Text book: 

1. Tom Mitchell, "Machine Learning", McGraw Hill, 1997.

2. Text book slides are here.