Machine Learning Foundations, Fall 2018

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

• instructor: Hsuan-Tien Lin (htlin AT csie . ntu . edu . tw) [office hour: after classes, or by appointment]
• TAs and TA hour: ml_ta AT csie . ntu . edu . tw
  • Chien-Min Yu: Mondays 10:00--11:00, CSIE R536
  • I-Ting Chen: Wednesdays 10:00--11:00, CSIE R536
  • Chia-You Chen: Wednesdays 18:00--19:00, Red Sofa at CSIE Basement
  • Yu-Ting Chou: Thursdays 11:00--12:00, CSIE R536
  • Wei-I Lin: Fridays 9:00--10:00, Red Sofa at CSIE Basement
  • Chun-Yi Tu: Fridays 14:00--15:00, CSIE R536

  Course Information

  • Time: Tuesdays 12:20 to 14:10
  • Room: CSIE Building, R103
  • Textbook: Learning from Data, by Yaser Abu-Mostafa, Malik Magdon-Ismail and Hsuan-Tien Lin
  • Language: Mandarin teaching with English slides
  • Grading: 100% homework (tentative)
  • Full Course Website: http://ceiba.ntu.edu.tw/1071mlfound

  Announcements

  • homework 4 announced on 12/18/2018, to be due on 1/15/2019
  • homework 3 announced on 12/18/2018, to be due on 1/15/2019
  • homework 2 announced on 10/30/2018, to be due on 12/11/2018
  • homework guidelines announced on 10/26/2018
  • homework 1 announced on 10/2/2018, to be due on 10/30/2018
  • sign up here if you want to enroll
  • homework 0 announced on 08/20/2018, self-graded
  • policy announced on 08/20/2018

  Class Policy

  • main policy
  • homework guidelines

  Course Plan (tentative)

  date	syllabus	todo/done	suggested reading
  09/11	course introduction; topic 1: when can machines learn?		course slides
  09/18	the learning problem		course slides; LFD 1.0, 1.1.1, 1.2.4
  09/25	learning to answer yes/no		course slides; LFD 1.1.2, 3.1
  10/02	types of learning	homework 1 announced	course slides; LFD 1.2; LFD 1.3
  10/09	feasibility of learning		course slides; LFD 1.3
  10/16	topic 2: why can machines learn? training versus testing		course slides; LFD 2.0, 2.1.1
  10/23	theory of generalization		course slides; ; LFD 2.1.2
  10/30	the VC dimension; noise and error	homework 1 due; homework 2 announced	course slides; course slides; LFD 2.2; LFD 1.4
  11/06	topic 3: how can machines learn? linear regression		course slides; LFD 3.2
  11/13	logistic regression		course slides; LFD 3.3
  11/20	linear models for classification		course slides; LFD 3.3 (for SGD part only)
  11/27	nonlinear transformation		course slides; LFD 3.4
  12/04	no class because of NIPS
  12/11	topic 4: how can machines learn better? hazard of overfitting	homework 2 due; homework 3 and homework 4 announced	course slides; LFD 4.0, 4.1
  12/18	regularization		course slides; LFD 4.2
  12/25	validation		course slides; LFD 4.3
  1/1	no class because of new year holiday
  1/8	three learning principle		course slides; LFD 5
  1/15	winter vacation begins (really?)	homework 3 and homework 4 due

  ---

  Last updated at CST 13:08, October 04, 2023 Please feel free to contact me: