1. Lecture 00: Introduction
CS480/680: Intro to ML
Lecture 00: Introduction
1/13/2019
Yao-Liang Yu

2. Outline
Course Logistics
Course Overview
1/13/2019
Yao-Liang Yu

3. Outline
Course Logistics
Course Overview
1/13/2019
Yao-Liang Yu

4. Course Info Instructor: Yao-Liang Yu (yaoliang.yu@uwaterloo.ca)
Office hours: DC 3617, TTh 11:30 – 12:30
TAs: Hamidreza Shahidi (h24shahi), Jingjing Wang (jj27wang),
KaiWen Wu (k77wu), Lian Xin (x9lian)
Website: cs.uwaterloo.ca/~y328yu/mycourses/480
Syllabus, slides, notes, policy, etc.
Piazza: piazza.com/uwaterloo.ca/fall2018/cs480cs680/
Announcements, questions, discussions, etc.
Learn:
Assignments, solutions, grades, etc.
1/13/2019
Yao-Liang Yu

5. Prerequisites Programming Mathematical maturity CS341, CS370/371
Basic probability, statistics, algorithms, linear algebra, calculus
Mathematical maturity
Programming
1/13/2019
Yao-Liang Yu

6. What to expect
1/13/2019
Yao-Liang Yu

7. Textbook No required textbook
Lecture notes or slides will be posted on course web
Some fine textbooks:
1/13/2019
Yao-Liang Yu

8. Assignments 4 assignments with the following tentative plan:
Submit on LEARN. Submit early and often.
Typeset using LaTeX is recommended
Out date
Due date
CS480
CS680 A1
Sep. 11
Sep. 27
10% A2
Oct. 16 A3
Nov. 8 A4
Nov. 27
Proposal
Oct. 23 5%
Report
Dec. 3
15%
30%
1/13/2019
Yao-Liang Yu

9. Exam Midterm: 20%, Oct 18, in class Final exam: 40%, date TBA
Open book
No electronics
1/13/2019
Yao-Liang Yu

10. Policy Do your own work independently and individually
Discussion is fine, but no sharing of text or code
Explicitly acknowledge any source that helped you
Ignorance is no excuse!
Good online discussion, more on course website
Serious offence will result in expulsion…
NO late submissions!
Except hospitalization, family urgency, …
Appeal within two weeks, otherwise final
1/13/2019
Yao-Liang Yu

11. Project Optional: 480/680 can trade for midterm/final, resp.
You project should
Relate to machine learning (obviously)
Allow you to learn something new (and hopefully significant)
Be interesting and nontrivial (publishable)
2-page proposal and <= 8 pages report
1/13/2019
Yao-Liang Yu

12. Grades
1/13/2019
Yao-Liang Yu

13. Enrollment If you already enrolled If you are not enrolled yet
Good for you!
Please take a look at the quiz and decide if you are comfortable with the background
If you are not enrolled yet
Please complete the quiz and hand in on next Tuesday
Permission numbers will be based on that
cs.uwaterloo.ca/~y328yu/mycourses/480/quiz.pdf
1/13/2019
Yao-Liang Yu

14. Questions?
1/13/2019
Yao-Liang Yu

15. Outline
Course Logistics
Course Overview
1/13/2019
Yao-Liang Yu

16. What is Machine Learning (ML)?
“Machine learning is the field of study that gives computers the ability to learn without being explicitly programmed.” --- Arthur Samuel (1959).
“A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.” --- Tom Mitchell (1998)
1/13/2019
Yao-Liang Yu

17. Why is ML important for YOU?
First off, you use ML everyday
Lots of cool applications
Excellent for job-hunting
1/13/2019
Yao-Liang Yu

18. Learning Categories Supervised Reinforcement Unsupervised
Classification
Regression
Ranking
Reinforcement
Control
Pricing
Gaming
Unsupervised
Clustering
Visualization
Representation
Teacher provides answer
Teacher provides motivation
Surprise, surprise
1/13/2019
Yao-Liang Yu

19. How do humans learn?
1/13/2019
Yao-Liang Yu

20. Supervised learning
1/13/2019
Yao-Liang Yu

21. Formally Given a training set of pairs of examples (xi, yi)
Return a function f: X  Y
On an unseen test example x, output f(x)
The goal is to do well on unseen test data
Usually do not care about performance on training data
1/13/2019
Yao-Liang Yu

22. Reinforcement learning
Not in this course…
CS486/686
Silver et al., Nature’16
Abbeel et al., NIPS’06
1/13/2019
Yao-Liang Yu

23. Unsupervised learning
Let the data speak for itself!
Le et al., ICML’12
1/13/2019
Yao-Liang Yu

24. Focus of ML research Representation and Interpretation Generalization
How to represent the data? How to interpret result?
Generalization
How well can we do on test data? On a different domain?
Complexity
How much time and space?
Efficiency
How many samples?
Applications
1/13/2019
Yao-Liang Yu

25. Course Overview
1/13/2019
Yao-Liang Yu

26. Gimme, Gimme more Science special issue on AI
Nature special issue on AI
As always, google and wikipedia are your friends.
1/13/2019
Yao-Liang Yu

27. Questions?
1/13/2019
Yao-Liang Yu