Hsuan-Tien Lin

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


Machine Learning Foundations, Fall 2016

Course Description

Machine learning is the study that allows computers to adaptively improve their performance with experience accumulated from the data observed. The course teaches the most fundamental algorithmic, theoretical and practical tools that any user of machine learning needs to know.

People

Course Information

Announcements

Class Policy

Course Plan (tentative)

datesyllabustodo/donesuggested reading
9/20information session: course introductioncourse slides; course FAQs
11/15no class because of NTU anniversary
11/17topic 1: when can machines learn?
the learning problem
course slides; LFD 1.0, 1.1.1, 1.2.4
11/22learning to answer yes/no course slides; LFD 1.1.2, 3.1
11/24types of learning; feasibility of learningcourse slides; LFD 1.2; course slides; LFD 1.3
11/29topic 2: why can machines learn?
training versus testing
course slides; LFD 2.0, 2.1.1
12/1theory of generalizationhomework 1 announcedcourse slides; LFD 2.1.2
12/6the VC dimensioncourse slides; LFD 2.2
12/8noise and errorcourse slides; LFD 1.4
12/13topic 3: how can machines learn?
linear regression
course slides; LFD 3.2
12/15logistic regression homework 2 announcedcourse slides; LFD 3.3
12/20linear models for classification course slides; LFD 3.3 (for SGD part only)
12/22nonlinear transformation course slides; LFD 3.4
12/27topic 4: how can machines learn better?
hazard of overfitting
course slides; LFD 4.0, 4.1
12/29regularization homework 3 announcedcourse slides; LFD 4.2
1/3validation course slides; LFD 4.3
1/5three learning principles homework 4 announcedcourse slides; LFD 5
1/10backup slot (will have class only if we cannot finish teaching all 16 lectures)

Last updated at CST 13:07, October 04, 2023
Please feel free to contact me: htlin.email.png
Valid HTML 4.0!