Hsuan-Tien Lin > Courses > Machine Learning, Fall 2024

Hsuan-Tien Lin

Home | MOOCs | AIsk | Courses | Research Group | Awards | Publications | Presentations | Programs/Data

Machine Learning, Fall 2024

Course Description

Machine learning allows computational systems to adaptively improve their performance with experience accumulated from the data observed. This course introduces the basics of learning theories, the design and analysis of learning algorithms, and some applications of machine learning.

People

instructor: Hsuan-Tien LIN (htlin AT csie . ntu . edu . tw) [office hour: after classes, or by appointment]
TAs and TA hour: html_ta AT csie . ntu . edu . tw
- Yun-Ye Cai, Computer Science and Information Engineering
- Chia-Wei Chang (VP of Project), Computer Science and Information Engineering
- Shu-Han Chang, Physics
- Chia-Le Chen, Atmospheric Science
- Chu-Hsin Chen, Computer Science and Information Engineering
- Chien-Yi (Chris) Chien (VP of Assignments), Computer Science and Information Engineering
- Shih-Hsuan Chou, Physics
- Mai Tan Ha (Head TA), Computer Science and Information Engineering
- Bo-Kai Huang, Computer Science and Information Engineering
- Chien-Jui Huang, Computer Science and Information Engineering
- Hsiao-Chieh Kao, Engineering Science and Ocean Engineering
- Yu-Wei Kuan, Computer Science and Information Engineering
- Hsun-Yu (Yoyo) Lee, Information Management
- I-Pei Lee, Electrical Engineering
- Ren-Wei Liang, Computer Science and Information Engineering
- Zhi-Bao Lu, Computer Science and Information Engineering
- Wei-Po Wang, Physics
- Chun-Hao Yang, Computer Science and Information Engineering

Course Information

Time: Mondays 13:20 to 16:20
Room: CSIE R103 (with broadcast to R104, R105, R107 and screencast link below)
NTU COOL: https://cool.ntu.edu.tw/courses/40495
Synchronous Screencast: here, containing slido interaction at #HTML2024FALL
Textbook: Learning from Data, by Yaser Abu-Mostafa, Malik Magdon-Ismail and Hsuan-Tien Lin
Language: English teaching
Grading: 70% homework, 30% project (tentative)

Announcements

2024/10/07: homework 3 announced, due on 10/21
2024/09/23: homework 2 announced, due on 10/07
2024/09/09: homework 1 announced, due on 10/07
2024/09/02: homework 0 announced, due on 10/07
2024/08/13: course policy announced here

Class Policy

policy

Course Plan (tentative)

date	syllabus	todo/done	materials
09/02 (W1)	course introduction; topic 1: when can machines learn? the learning problem	homework 0 announced	recording from YouTube screencast slides for course introduction (bug in p6/p12 fixed at 09/03 06:00) slides for the learning problem; LFD 1.0, 1.1.1, 1.2.4
09/09 (W2)	learning to answer yes/no; types of learning	homework 1 announced	recording from YouTube screencast slides for learning to answer yes/no (bug in p10 fixed at 09/16 08:30); LFD 1.1.2, 3.1 slides for types of learning; LFD 1.2; LFD 1.3
09/16 (W3)	feasibility of learning; topic 2: why can machines learn? training versus testing		recording from NTU CSIE (uploaded to YouTube)---we are very sorry that there was an Internet issue and screencasting does not work that day slides for feasibility of learning; LFD 1.3 suggested extended reading: The Lack of A Priori Distinctions Between Learning Algorithms (Wolpert) slides for training versus testing; LFD 2.0, 2.1.1
09/23 (W4)	(optional)theory of generalization; the VC dimension; noise and error	homework 2 announced	recording from YouTube screencast slides for the VC dimension; LFD 2.2 slides for noise and error; LFD 1.4 optional: slides for theory of generalization ; LFD 2.1.2 English-teaching Lecture 6 by Prof. Yaser Abu-Mostafa at Caltech Mandarin-teaching Lecture 6 by Prof. Hsuan-Tien Lin at NTU: part 1, part 2, part 3, part 4
09/30 (W5)	topic 3: how can machines learn? linear regression; logistic regression		recording from YouTube screencast slides for linear regression; LFD 3.2 slides for logistic regression; LFD 3.3
10/07 (W6)	linear models for classification; nonlinear transformation	homework 0 due; homework 1 due; homework 2 due; homework 3 announced	recording from YouTube screencast slides for linear models for classification; LFD 3.3 slides for nonlinear transformation; LFD 3.4
10/14 (W7)	topic 4: how can machines learn better? hazard of overfitting; regularization		slides for hazard of overfitting; LFD 4.0, 4.1 slides for regularization; LFD 4.2
10/21 (W8)	validation; three learning principles	homework 3 due; homework 4 announced; final project announced	slides for validation; LFD 4.3
10/28 (W9)	topic 5: how can machines learn by embedding numerous features? linear support vector machine; dual support vector machine
11/04 (W10)	kernel support vector machine; soft-margin support vector machine	homework 4 due; homework 5 announced
11/11 (W11)	topic 6: how can machines learn by combining predictive features? blending and bagging; adaptive boosting
11/18 (W12)	decision tree; random forest; gradient boosted decision tree	homework 5 due; homework 6 announced
11/25 (W13)	topic 7: how can machines learn by distilling hidden features? neural network; (preliminary) deep learning
12/02 (W14)	modern deep learning	homework 6 due; homework 7 announced
12/09 (W15)	no class as instructor needs to attend ACML 2024 and NeurIPS 2024; recording: machine learning for modern artificial intelligence
12/16 (W16)	finale	homework 7 due
12/23 (W17)	no class and winter vacation started (really?)	final project due

Last updated at CST 08:56, October 14, 2024
Please feel free to contact me: htlin.email.png