Professor Sankararaman is an amazing lecturer, and he explains concepts in a clear and concise manner. For my quarter, there were eight quizzes in total (pretty much one per week), which was somewhat inconvenient. However, I learned a lot from this class, and it was overall a highly enjoyable experience. I would definitely recommend taking this class with this professor.

this class is so damn hard and so boring. its literally all theory, the homeworks and midterm were so much more difficult. everything seems so abstract because we dont run thru examples of how to use these ml models. wish i never took this class (and im a cs major)

grades were curved down. homework 50%, midterm 20%, and final 30%. if ur exam scores on midterm and final are higher than the median, and did all the homework, u should secure a B+ at least. not a easy class if u have no prior knowledge in ML.

First time leaving a review bc this class is confusing as f. Hard time for a cs and math double major to understand what this class is talking abt bc the professor doesn’t explain at all. Midterm median is 76 and final median is 80. Not sure if a curve will be applied. If you want an easy GE, avoid this one.

Absolutely loved Professor Sankararaman. The way he is able to so clearly articulate convoluted and confusing concepts and teach things in a clear, digestable way is such a gift, and he is such a patient, kind person. His lectures are so well delivered and organized, and it's evident how insanely knowledgable he is on what he is teaching that the jam packed 2 hours of class where everything he says is purposeful and clear feels like he could do it in his sleep. Probably the best professor I've had at UCLA (I'm graduating as I write this!) This was an extremely challenging, densely packed course, but I took away so much from it and feel that I have a solid grasp on the fundamentals of Machine Learning and different models.

Improvements for this course is that I wish it provided more understanding and intuition, possibly even review of the basics linear algebra. Maybe for future courses the TAs can spend the first discussion reviewing intuition of linear algebra concepts--linear transformations, inner products, projections, vectors, matrix operations, etc. For me, if class's concepts are hard, I can keep thinking about them and mulling them over and understand them but I cannot suddenly grasp linear algebra and visualize matrix operations and vector operations. It felt like I was just memorizing what PSD, eigenvectors, etc are for the exam and I don't really understand at all what is going on. Same for things like Lagrange optimization, I felt like the math can get so tricky and I don't know what I'm doing, even though I understand the intuition behind the concepts. I also felt that some MCQ questions on the midterm were "trick"questions that weren't necessarily covered in class.

This class is very theory and math/proof heavy, which I struggled with as a Data Engineering Minor. Long, long proofs in class for machine learning models, difficult to focus on. The homework assignments were some light math assignments, then Python coding. The midterm exam was easy, the final exam was the hardest exam of my entire life. If you need to take this class, this professor is a solid choice.

Go to lectures, they're good. Go to OH, Prof. Sriram is a nice guy. Take the homeworks seriously and start early, they take less than 5 hours each on average and there are only 4. Pretty frustrated to see people ask for extensions when they aren't really needed. (We have 2 ! weeks per pset). Midterm median was pretty high (it was also way too easy) at 93. Final exam was harder (relatively speaking, but not hard in general. Pset level of difficulty for the questions) with median of 74.5. We could have been downcurved this quarter if the average was higher. For that reason, I thank the DSE minors who took this class.

Sriram is one of the best professors I have had at UCLA. He genuinely cares about students' learning and answers any questions. There are 4 problem sets, which are kinda long and are each worth 10%, but if you start early/with others they're cash. Quizzes every 2 weeks, with the lowest one being dropped, and each worth 5% (4 counted quizzes), which are pretty easy most weeks but can be a bit tougher towards the end. Midterm and Final were both 20%, and the midterm was easy, with the final being tougher. Overall, a great CS class and elective, would highly recommend to anyone.

If you want an easy A look no further

The instructor is the best one that I've ever had in UCLA.
There are 4 labs for 40% of your grades, 6 quizzes, the first one is math review is not count as graded one, from other 5 quizzes he will drop the lowest one and 4 remaining quizzes worth of 20% of your grade, and final and midterm both have each 20% of the grades.
Both exams are open books and open notes and both are in person.
He always use slides and they will posted before the class for students to use to take a note during the class.
Annotated slides also will be posted after each class.
He is caring, super organized, and clear on his explanation if you ask questions in his class you do not feel you are dumb, he is patient to go over the concepts and explain until students to understand.
I highly recommend to take the class with him if you want to really understand something about machine learning you should take this class with him.