- Josh Gardner, email@example.com (Head TA)
- Gantcho Dimitrov, firstname.lastname@example.org
- Jakub Filipek, email@example.com
- Alyssa La Fleur, firstname.lastname@example.org
- Tim Li, email@example.com
- Vlad Murad, firstname.lastname@example.org
- Long Thanh Nguyen, email@example.com
- Morgan Putnam, firstname.lastname@example.org
- Esteban Safranchik, email@example.com
- Jackson V Stokes, firstname.lastname@example.org
- Kyle Guohao Zhang, email@example.com
- Lecture time and place: MWF 9:30 -- 10:20am, in CSE2 G20
- Ed discussion board (link)
All questions that are not of a personal nature should be posted to the discussion board. You will be automatically added to the course on Ed; please contact us if you have access issues.
- Staff can be reached at the email address firstname.lastname@example.org.
- Submit anonymous feedback here (we will not be able to respond)
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: Your grade will be based exclusively on 5 homework assignments: HW0 (10%), HW1 (20%), HW2 (20%), HW3 (20%), HW4 (30%). There are no exams or credit given in any way other than the homeworks (e.g., no credit given for attending lecture or section).
However, depending on whether you are enrolled in 446 or 546, the way the assignments are graded or curved varies (see below).
In the past, CSE 446 was the undergraduate machine learning course, and CSE546 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, this course offers three different versions of the course concurrently.
A detailed overview of the difference between the courses and eligibility is below.
||CSE2 G20, MWF 9:30 -- 10:20am
||Attend the section you are registered for on Zoom
||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 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.
||CSE2 G20, MWF 9:30 -- 10:20am
||A and B problems.
||You will be graded (e.g., curved) against your peers in 546 only.
Your grade on the A and B problems will be curved seperately, and then summed.
For example, if you you recieved a (curved) score of 0.9 on the A problems, and a (curved) score of 0.8 on the B problems, then your full grade on your transcript will be (3.8)*(0.9) + (0.2)*(0.8) = 3.58, rounded to 3.6.
If only the A problems on the homework are attempted, the highest score attainable is a 3.8. If only the B problems are attempted, the highest score attainable is a 0.2.
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, but please do not monopolize the time as these these sections were intended for students enrolled in 446. So feel free to be a fly on the wall or lurker in 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 the 3.8 that is based on 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 graduate student and busy with research so doing the A problems alone is attractive. But I need a 3.4 for the course to count, 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. The only difference is that if you only attempt the A problems, the highest grade you can achieve is 3.8.
- 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.