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.

Lectures are clear and slides are provided.

There are easy quizzes most weeks.
There are easy problem sets with coding sections.
The final was easy compared to the EC ENGR C147 midterm (took in same quarter).
C147 helps with M146 more than M146 helps with C147.
Machine learning topics aren't viewed from a big-picture perspective and aren't really related to each other from week to week.
Machine learning topics are pretty boring.

Overall a great intro class to ML, a good prep course for C147

Didn't attend a single lecture but the class is popular and well-structured. The TAs are very knowledgeable and very quick in grading. ML concepts are boring though.

echo the rest of the reviews this man is the goat

Class structure: Problem sets every two weeks, quizzes every week, final at the end
Lectures: engaging prof and great slides mean lectures were (mostly) easy to listen to. I watched them a day after on 1.25 or 1.5 speed, and that was great for me. I downloaded all the slides to reference later on.
PSets: if you watched lectures, know how to do some advanced calculus, and have a copy of the slides handy, you should be able to do all the conceptual problems in these PSets (roughly 50% of the points on each PSet). Additionally, they encourage you to discuss with other classmates to "check answers" and whatnot. The coding portions at the end of the PSets (50%) are super fun and straightforward. They give very detailed instructions and you get to see how machine learning works on real datasets.
Quizzes: also very straightforward. Plugging numbers into formulas (have to know which formula to use!) and having the sides handy to ctrl+F is imperative. I found that there was more than enough time to answer each question. They are all multiple choice.
Final: basically a long quiz.

Nice prof, cool material, good format

Take it. The professor is very passionate about teaching and give clear instructions on what is going on every lecture. The slides are not very creative but they are clear enough even for self-study. The homework and problem sets are fairly assigned and graded. This class does not involve a lot of coding, so it is one of the easiest CS upper I have ever taken. He will give skeleton code, and all you have to do is to fill in the "to do" parts according to instructions, where everything is done in python. For lectures and exams, I feel it is more math and stats focused, but with the foundation is Stats 100A or other equivalents, one will be fine on those stuff. Honestly, easy A for a CS upper.

This is a great class to take. The concepts are covered very well and the tests and homework’s are very fair. The material gets harder after week 5 as you do kernels and SVMs, so make sure to keep attending lecture. The grading scheme is tough so make sure you don’t lose points on the homework

Siriam is an awesome professor. The class is very well-organized. There are several TAs who each hold lots of office hours throughout the week. The only complaint I have is grades were curved down at the end of the quarter.

Highly recommend this class for those wanting a better mathematical foundation in machine learning and knowledge of the basic algorithms. The homeworks are mostly math problems and proof related to machine learning concepts, and usually the last problem involves programming one of the algorithms you learned in class. The tests are pretty much the same, minus the programming parts.
Sriram was a fine professor. He could be a little eccentric and sometimes go too quickly with the concepts + math proofs, but for the most part he and his TAs did a good job of making sure you could understand the concepts and the homeworks. Overall I recommend him as a teacher.