Hsuan-Tien Lin > Courses > Machine Learning, Fall 2009

Hsuan-Tien Lin

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

Machine Learning, Fall 2009

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.

Course Information

Instructor: Hsuan-Tien Lin (htlin AT csie DOT ntu DOT edu DOT tw)
office hour: after class, R104, or by appointment, R314
TA: Chun-Wei Liu, Te-Kang Jan, Ken-Yi Lin (ml09fall AT csie DOT ntu DOT edu DOT tw)
TA hour:
(Regular) Fridays noon to 2pm when there is a homework due, R106
(For HW0 only) 9/17/2009 noon to 2pm, R106
Time: Mondays 14:20--17:20 (we will take a long break around 15:50)
Room: R104 of the CSIE building
Textbook: Learning from Data, by Yaser Abu-Mostafa, Malik Magdon-Ismail and Hsuan-Tien Lin (draft version)
Language: English
Grading: 70% homework, 30% project (tentative)
Full Course Website: http://ceiba.ntu.edu.tw/981ML

Announcements

the deadline of final project is extended to 1/15/2010 4pm
the deadline of homework 6 is extended to 12/29/2009 4:20pm
homework 7 released on 12/28/2009, due 1/4/2010
homework 6 released on 12/21/2009, due 12/28/2009
final project released on 12/14/2009, due 01/11/2010
homework 5 released on 11/23/2009, due 12/07/2009 (two weeks)
some words from the TAs about homework 3
homework 4 released on 11/02/2009, due 11/16/2009 (two weeks)
homework 3 released on 10/19/2009, due 10/26/2009
As there is no usage on the discussion forum of CEIBA, we have decided to close it. The questions related to the class can be discussed through the TA email account, and will be propagated to the class when necessary. The questions related to the book can go to the book forum directly.
homework 2 released on 10/05/2009, due 10/12/2009
note that there would be no TA hour on 10/2/2009; the TA hour would be held only when there is a homework due
the source code uploading deadline of homework 1 is extended to 09/29/2009 4:00am because CEIBA is down
FAQs and some information about homework 1 added on 09/23/2009
homework guidelines announced on 09/23/2009
homework 1 released on 09/21/2009, due 09/28/2009
another bug of homework 0 fixed on 09/17/2009 :-P
TA hour for homework 0 will be held from noon to 2pm on 9/17/2009 (Thursday) in R106
a bug of homework 0 fixed on 09/15/2009
homework 0 released on 09/14/2009, no due date (self-graded)

Class Policy

main policy, as explained in class
a reminder that you must write your homework in English

Course Plan (tentative)

date	syllabus	todo/done	suggested reading
2009.09.14	introduction	homework 0 released main policy released and explained	taught in class: Page 1-1 of LFD Page 1-4 of LFD reading assignments: Section 1.1 of LFD
2009.09.21	introduction/perceptrons/learnability	homework 1 released about this class homework guidelines announced	taught in class: Subsection 1.2.1 of LFD Section 1.3 of LFD (partially) Page 1-20 of LFD reading assignments: Subsection 1.2.2 of LFD Section 1.3 of LFD
2009.09.28	generalization	homework 1 due	taught in class: Subsection 1.4.1, 1.4.2, and 1.4.3 (parts) of LFD reading assignments: Subsection 1.4.3 of LFD
2009.10.05	generalization/VC inequality	homework 2 released	taught in class: Pages 2-4 to 2-7 of LFD reading assignments: Pages 2-1 to 2-4 of LFD
2009.10.12	VC inequality/PLR resolved	homework 2 due	taught in class: Pages 2-8 to 2-12 of LFD The VC proof (as handout in class) Proof of PLR convergence (on board) reading assignments: Pages 2-13 to 2-14 of LFD Subsection 2.1.3 of LFD Section 2.2 of LFD (will be discussed later)
2009.10.19	linear model	homework 3 released	taught in class: Pages 3-1 to 3-5 of LFD linear programming, gradient descent, and stochastic gradient descent for linear classification reading assignments: Example 3.1 of LFD
2009.10.26	linear model	homework 3 due	taught in class: Pages 3-8 to 3-10 of LFD reading assignments: Pages 3-11 to 3-13 of LFD
2009.11.02	linear model/overfitting	homework 4 released	taught in class: some words from the TAs about homework 3 Sections 3.3, 4.1, 4.2 and 4.3 of LFD reading assignments: Example 3.2 of LFD Section 3.4 of LFD Subsections 4.2.3 and 4.3.2 of LFD
2009.11.09	overfitting/Neural Network	good luck with your other midterms	taught in class: Chapter 5 of LFD Notes on Neural Network (to be announced thru email)
2009.11.16	Neural Network	homework 4 due	taught in class: Notes on Neural Network (to be announced thru email) reading assignments: notes on the backprop algorithm from ML08Fall
2009.11.23	Neural Network/Support Vector Machine	homework 5 released	taught in class: Notes on Neural Network (to be announced thru email) SVM Introduction
2009.11.30	Bayesian and Unsupervised by Prof. Shou-de Lin		taught in class: Statistical Machine Learning (Bayesian) Unsupervised Learning
2009.12.07	Unsupervised and Machine Discovery by Prof. Shou-de Lin	homework 5 due	taught in class: Unsupervised Learning II From Learning to Discovery
2009.12.14	Bayesian/Support Vector Machine	final project announced	some notes for deriving dual SVM (similar to what we did in class) a short SVM tutorial a practical guide to support vector classification
2009.12.21	Support Vector Machine/Bagging/Boosting	homework 6 released
2009.12.28	Boosting	homework 6 due; homework 7 released	taught in class: slides on AdaBoost
2010.01.04	Boosting/Summary	homework 7 due
2010.01.11	Summary/Final Project Discussions	final project due good luck with your other finals	taught in class: Final Project Results

Last updated at CST 13:07, October 04, 2023
Please feel free to contact me: htlin.email.png