News!
- Midterm Location Update (as of 2/1) for 546 students. See exams
- Reminder: Midterm is this Friday, 2/7 @ 9:00am. See exams for more details
- We are currently grading HW1. We will get it back to you before the midterm
- Check out our new Staff Info page! (still under development)
Course Logistics
- Staff: See the Staff Info page for information about the staff
- Lecture time and place: Wednesdays, Fridays 9:00 -- 10:20am, KNE 110
About the Course, Prerequisites and Grading
Machine learning explores the study and construction of algorithms that can learn from historical data and make inferences about future outcomes.
This study is a marriage of algorithms, computation, and statistics so this class will be have healthy doses of each.
The goals of this course are to provide a thorough grounding in the fundamental methodologies and algorithms of machine learning.
Prerequisites: Students entering the class should be comfortable
with programming and should have a pre-existing working knowledge of
linear algebra (MATH 308), vector calculus (MATH 126), probability and
statistics (CSE 312/STAT390), and algorithms. For a brief refresher, we
recommend that you consult the linear algebra and statistics/probability
reference materials on the Textbooks page.
Grading: (tentative) Your grade will be based on 5 homework assignments: HW0 (8%), HW1 (13%), HW2 (13%), HW3 (13%), HW4 (13%). There will be one midterm worth 20% and a final worth another 20%.
However, depending on whether you are enrolled in 446 or 546, the way the assignments are graded or curved varies (see below).
Where to get help
- EdStem discussion board:
- Public/Anonymous Posts
- Questions like, "Is there a typo in the homework?", "What does this notation mean?", "Is this an accurate description of how this works?".
- Questions that are not of a personal nature should be posted to the discussion board.
- Private Posts
- Questions involving your own code should be posted privately to the EdStem discussion board, not office hours.
- Personal concerns (like "I was in the hospital", "Laptop was stolen").
- Course staff email cse446-staff@cs.washington.edu (only professors + admin TA):
- You do not need to email us to use one of the allowable late days, just go ahead and use it.
- Personal concerns (like "I was in the hospital", "Laptop was stolen") you aren't comfortable sharing with the entire staff. We highly recommend posting privately to EdStem if you are comfortable.
- Please direct all course-related inquiries to cse446-staff@cs.washington.edu or EdStem. Please do not email the instructors or TAs individually.
- TA office hours:
- Questions like, "How do I get started on problem 2?", "Am I on the right track?".
- We will not be able to give detailed code debugging help during office hours. It is too time-consuming for such a large class.
- Professor office hours:
- General conceptual understanding questions about the class, research or career advice.
- Questions about the homework are better suited to TA office hours.
- Gradescope should be used for all regrade requests.
- Submit anonymous feedback here.
Course offerings
In the past, CSE 446 was the undergraduate machine learning course, and CSE 546 was the graduate version. Over the years these courses have gotten closer and many undergraduates have opted to take the graduate version for a more challenging course. At the graduate level, some graduate students have sought a less demanding course to focus on research. To address the needs of our students, we are now offering two different versions of the course concurrently. A detailed overview of the difference between the courses and eligibility is below.
| Course |
Lecture |
Section |
Homework |
Grading |
| 446 |
KNE 110 WF 9:00 -- 10:20am |
Attend the section you are registered. |
A problems only. No credit will be rewarded for completing B problems. |
You will be graded (e.g., curved) against your peers in 446 only (on a 4.0 scale). For example, if you recieved a (curved) score of 0.9 on the A problems, then your full grade on your transcript will be (4.0)*(0.9) = 3.6. Any attempt of the B problems will not influence your grade in any way. |
| 546 |
KNE 110 WF 9:00 -- 10:20am |
None |
A and B problems. |
You will be graded (e.g., curved) against your peers in 546 only. You will be expected to complete both A and B problems. Midterm and final exams will be the same as 446, but you will be graded against 546 students.
|
Frequently Asked Questions
- I am registered for 446, is there any reason I should attempt a B problem? No.
- I am registered for 446, but I recognize that being enrolled in a graduate course may look good for graduate schools or employment in machine learning. Can I switch to 546? Yes! Please contact CSE advisors.
- I was registered for 446, decided to bump up to 546 and am now registered for 546. I now realize I regret the decision, can I switch back to being evaluated as a 446 student? No. You will be evaluated based on whatever course you are officially registered for.
- I am registered for 546. Can I attend a section of 446? Yes, you are welcome to attend any section of your choice. However, please give priority in terms of space and time to those students registered for the section.
- I am registered for 546. I started doing the B problems on the first couple homework assignments then stopped, will I be penalized for not attempting all of them? No. If you attempt any or none of the B problems at any time, your grade on the A problems is always unaffected. Attepting B problems can only help your grade above attempting the A problems alone.
- I am registered for 546. Do I need to notify instructors that I intend to complete the B problems? No. Just include them on your homework.
- I'm a CSE doctoral student and busy with research so doing the A problems alone is attractive. But I need a 3.4 for the course to count at quals, will I be unfairly judged for not attempting the B problems? No. The instructors are well aware of the grade requirements for graduate students and assign low grades with as much care as any course graded on a 4.0 scale.
- I am enrolled in 446 and my friend is enrolled in 546 but only attempted the A problems. On the A problems we received identical grades on the homeworks. Will the grades on our transcripts be the same? Potentially not. The courses are curved seperately and no attempt will be made to make grades comparable or "fair" across courses in any way.
- What is the formula for curving the courses? Will it be posted? No. Curving each course will be based on an affine transformation of scores up to the discretion of the instructors alone and will not be publicly posted.