lecture 00: introduction · 2018. 9. 6. · cs480/680: intro to ml lecture 00: introduction 1...
TRANSCRIPT
CS480/680: Intro to MLLecture 00: Introduction
9/6/2018 Yao-Liang Yu1
Outl ine
• Course Logistics
• Course Overview
9/6/2018 Yao-Liang Yu2
Outl ine
• Course Logistics
• Course Overview
9/6/2018 Yao-Liang Yu3
Course Info
• Instructor: Yao-Liang Yu ([email protected])• 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: https://learn.uwaterloo.ca• Assignments, solutions, grades, etc.
9/6/2018 Yao-Liang Yu4
Prerequisi tes
• CS341, CS370/371
• Basic probability, statistics, algorithms, linear algebra, calculus
9/6/2018 Yao-Liang Yu5
• Mathematical maturity
• Programming
What to expect
9/6/2018 Yao-Liang Yu6
Textbook
• No required textbook
• Lecture notes or slides will be posted on course web
• Some fine textbooks:
9/6/2018 Yao-Liang Yu7
Assignments
• 4 assignments with the following tentative plan:
• Submit on LEARN. Submit early and often.• Typeset using LaTeX is recommended
9/6/2018 Yao-Liang Yu8
Out date Due date CS480 CS680
A1 Sep. 11 Sep. 27 10% 10%
A2 Sep. 27 Oct. 16 10% 10%
A3 Oct. 16 Nov. 8 10% 10%
A4 Nov. 8 Nov. 27 10% 10%
Proposal Oct. 23 5% 10%
Report Dec. 3 15% 30%
Exam
• Midterm: 20%, Oct 18, in class
• Final exam: 40%, date TBA• Open book
• No electronics
9/6/2018 Yao-Liang Yu9
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
9/6/2018 Yao-Liang Yu10
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
9/6/2018 Yao-Liang Yu11
Grades
9/6/2018 Yao-Liang Yu12
Enrol lment
• If you already enrolled• 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
9/6/2018 Yao-Liang Yu13
Questions?
9/6/2018 Yao-Liang Yu14
Outl ine
• Course Logistics
• Course Overview
9/6/2018 Yao-Liang Yu15
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).
9/6/2018 Yao-Liang Yu16
• “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)
Why is ML important for YOU?
• First off, you use ML everyday
9/6/2018 Yao-Liang Yu17
• Lots of cool applications
• Excellent for job-hunting
Learning Categories
9/6/2018 Yao-Liang Yu18
Supervised
• Classification
• Regression
• Ranking
Reinforcement
• Control
• Pricing
• Gaming
Unsupervised
• Clustering
• Visualization
• Representation
Teacher provides answer Teacher provides motivation Surprise, surprise
How do humans learn?
9/6/2018 Yao-Liang Yu19
Supervised learning
9/6/2018 Yao-Liang Yu20
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
9/6/2018 Yao-Liang Yu21
Reinforcement learning
• Not in this course…
9/6/2018 Yao-Liang Yu22
• CS486/686
Silver et al., Nature’16Abbeel et al., NIPS’06
Unsupervised learning
• Let the data speak for itself!
9/6/2018 Yao-Liang Yu23
Le et al., ICML’12
Focus of ML research
• Representation and Interpretation• 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
9/6/2018 Yao-Liang Yu24
Course Overview
9/6/2018 Yao-Liang Yu25
Gimme, Gimme more
• Science special issue on AI
• Nature special issue on AI
• As always, google and wikipedia are your friends.
9/6/2018 Yao-Liang Yu26
Questions?
9/6/2018 Yao-Liang Yu27