Handout #1: Course Information
Meeting Times and Locations
Lectures: MW 9:30 AM - 10:50 AM,
(Huang Engineering Center)
Discussion sections: Fridays, 4:30 PM - 5:20 PM,
Gates B01 (recorded, optional attendance)
Office: Gates 156
Office: Sequoia 126
Office hours: Wednesdays 11:00 AM - 12:00 PM
Office: Gates 127
* - TAs marked with asterisk are Project TAs
If you and have a homework,
technical or general administrative question about CS229, for you to
get the fastest possible response, please post it on
forum. To contact the CS229 teaching staff directly, you can also
For telephone numbers and information about office hours (where we can
help you in person), see Office Hours and
This course provides a broad introduction to
machine learning and statistical pattern recognition. Topics include:
supervised learning (generative/discriminative learning,
parametric/non-parametric learning, neural networks, support vector
machines); unsupervised learning (clustering, dimensionality reduction,
kernel methods); learning theory (bias/variance tradeoffs; VC theory;
large margins); reinforcement learning and adaptive control.
The course will also discuss recent applications of machine learning,
such as to robotic control, data mining, autonomous navigation,
bioinformatics, speech recognition, and text and web data
Students are expected to have the following background:
- Knowledge of basic computer science principles and skills, at a level sufficient to write a reasonably non-trivial computer program.
- Familiarity with the probability theory. (CS 109 or STATS 116)
- Familiarity with linear algebra (any one of Math 104, Math 113, or CS 205)
There is no required text for this course.
Notes will be posted periodically on the course web site. The following
books are recommended as optional reading:
Course handouts and other materials can be downloaded from http://www.stanford.edu/class/cs229/materials.html
- Richard Duda, Peter Hart and David Stork, Pattern Classification, 2nd ed. John Wiley & Sons, 2001.
- Tom Mitchell, Machine Learning. McGraw-Hill, 1997.
- Richard Sutton and Andrew Barto, Reinforcement Learning: An introduction. MIT Press, 1998
- Trevor Hastie, Robert Tibshirani and Jerome Friedman, The Elements of Statistical Learning. Springer, 2009
- Home page: http://cs229.stanford.edu/
- Current quarter's class videos: Available here for SCPD students and here for non-SCPD students
- Piazza forum: http://piazza.com/stanford/fall2016/cs229
- Staff mailing list: email@example.com
NOTE: If sending email about a homework, please
state in the subject line which assignment and which question the email
refers to (e.g., Subject: Hwk3 Q1). Please send one
question per email. If you have a technical or homework or general administrative
question that is not confidential or personal, we strongly encourage you to post
it on the Piazza forum instead,
as that will get you a faster response; make a private note if necessary
Homeworks and Grading
There will be four written homeworks, one midterm,
and a major open-ended term project. The assignments will contain written questions and
questions that require some Matlab programming. In the term project,
you will investigate some interesting aspect of machine learning or
apply machine learning to a problem that interests you.
We try very hard to make questions unambiguous, but some ambiguities
may remain. Ask if confused or state your assumptions explicitly. Reasonable
assumptions will be accepted in case of ambiguous questions.
will be based 40% on homeworks (10% each),
20% on the midterm and 40% on the major term project.
We strongly encourage students to form
study groups. Students may discuss and work on homework problems in groups.
However, each student must write down the solutions independently, and without
referring to written notes from the joint session. In other words, each
student must understand the solution well enough in order to reconstruct
it by him/herself. In addition, each student should write on the problem
set the set of people with whom s/he collaborated.
Further, since we occasionally reuse problem set questions from
previous years, we expect students not to copy, refer to, or look
at the solutions in preparing their answers. It is an honor code
violation to intentionally refer to a previous year's solutions.
This applies both to the official solutions and to solutions that
you or someone else may have written up in a previous year.
Each student will have a total of seven
free late (calendar) days to use for
homeworks, project proposals and project milestones.
Once these late days are exhausted, any assignments turned in late will be
penalized 20% per late day. However, no assignment will be accepted
more than three days after its due date, and late days cannot be used
for the final project poster or writeup. Each 24 hours or part thereof that a
homework is late uses up one full late day.
We will be using Gradescope to handle assignment submissions. Entry code for Gradescope is 9GK339.
Hard copy and email submissions will not be accepted.
The term project may be done in teams of up to three persons. The
midterm is open-book/open-notes, and will cover the material of the
first part of the course. It will take place on Wednesday, November 9, 2016 from 6-9 PM. The exam venue will be announced soon.
Assignment 0 is a dummy assignment that will allow you to get used to the Gradescope submission process, and it is due on 10/05 at 11:00 AM. It is worth 0 points.
When you submit your assignment, make sure to tag all the pages for each problem according to Gradescope's submission directions. Graders may deduct points on problems that are difficult to find.
The due dates on Gradescope will be the hard deadlines, after which we will not accept submissions. On-time submissions should be made before the deadlines listed on the website. Do not confuse the hard deadline on Gradescope with the deadlines on the website.
We strongly encourage typesetting your assignments. If the grader cannot read your assignment for whatever reason (handwriting, photo/scanning quality, etc.), you will not receive credit for that work.
Regrades will also be handled through Gradescope. We will begin to accept regrades for an assignment the day after grades are released for a window of three days. We will not accept regrades for an assignment outside of that window. Regrades are intended to remedy grading errors, so regrade requests must discuss why you believe your answer is correct in light of the deduction you received. We do not accept regrade requests of the form "I deserve more points for this" or "that deduction is too harsh." If you submit a regrade request of this form, you will receive further deductions. When you submit a regrade request, the grader may review your entire assignment, in which case you may lose points on other questions. Your score on an assignment may decrease if you submit for a regrade.
To review material from the prerequisites or to supplement the lecture
material, there will occasionally be extra discussion sections held on
Friday. An announcement will be made whenever one of these sections is
held. Attendance at these sections is optional.
Communication with the Teaching Staff
If you have a question that is not confidential or personal, encourage
you to post it on our forum on Piazza.
To contact the teaching staff directly, we strongly encourage you to come to office hours.
If that is not possible, you can also email us at the course staff list,
of the TAs and the professor). By having questions sent to all of us,
you will get answers much more quickly. Of course, confidential or personal questions
can still be sent directly to Prof. Ng, Prof. Duchi or the TAs.
Answers to commonly asked questions and clarifications
to the homeworks will be posted on the FAQ.