Daniel Hsu

There's 3 exams worth 90% of your grade. This class is a time sink if you want to do well. Lectures: expect 3+ hours per lecture to really understand (rewatching, pausing, filling gaps, re-deriving steps). Prereq math review: if you haven’t touched linear algebra / probability / calc in years (like most people), budget ~10 hours/week just to re-learn the prereqs. The prereq expectations are kind of ridiculous because basically nobody has “fresh” mastery of all of it unless they just took those classes and actually retained them. Homework: if you want real practical skills and you actually do the programming components seriously, it can be ~20 hours per homework (of which there are 6 of). Bare minimum survival mode (to not drown / to do okay): -focus on lecture material and prioritize understanding -do the theory parts of homework -do the quizzes (completion based and worth 10% of final grade) -do practice exam problems Extra mile: -do the readings (painful, but it helps a lot for exams) -do the implementation homework problems (take away some practical ability from the course)

Reading reflections each class 2 hard homework assignments 1 lecture to give 1 lecture to scribe 1 final project based on reading and original research

This is a high value course for any aspiring SWE in the age of AI — but it will probably make you miserable, and it could be run so much better. You will learn the theoretical underpinnings of the core “meat and potatoes” supervised ML methods (linear/logistic regression, neural nets, etc.). The problem is the teaching. The professor is a bad lecturer: he nonchalantly skips steps in highly abstract math, leaves out key details, and then effectively dumps the missing reasoning into the required readings, which are insanely dense. Also, he has a serious attitude problem — he can be dismissive and unkind when students ask questions, which makes it harder to engage and learn. The readings are basically hieroglyphics. I’m not exaggerating: it can take hours to get through a single page if you actually want to understand what’s going on. There’s also a big mismatch between “what you do” and “what gets graded.” The optional homework is the only place you get hands-on practice with ML in Python, so the class barely values practical skill. You can ignore the programming parts of the homework and not worry much about exam performance, because the exams are theory-heavy and don’t care whether you can implement well. Grading is harsh and the curve is absurd — it's literally curved to the C range, which is ridiculous considering how demanding the prerequisites and workload are. I ended up…

This was an advanced class in learning theory that focused on "interactive learning" which attempts to model situations where a "learner" can "interact" with his "teacher". Each week, we read a few papers in the field and went through the details in class. At the start of the class, we did some classic results in using expert advice and bandit problems; this material is definitely worthwhile if you have not seen it before. But the rest of the papers were a lot more recent. However, I was not particularly inspired by the papers; they seemed to spend a lot of time defining new learning models which were often infeasible in practice and not overwhelmingly interesting in their own right. Aside from definitions, few of the actual algorithms had novel proofs. More than half of the classes had student lecturers which were of a rather inconsistent quality. I think I would have learned more if Professor Hsu had taught them all. Hsu also has a bit of a stick up his rear. He spilled a lot of ink making very detailed class requirements, but in the end he gave almost everyone near-perfect grades. He constantly complained about barely late students and has needlessly specific instructions for everything, which made the assignments more work than they were worth. Often, he does not seem to understand student questions or answers them kind of dismissively. Despite being a good lecturer and an…

Avoid at all cost. The curve is non-existent. Mean will get you a C/C+ as oppose to B/B+ in other classes.

90% is exam, he ends up giving 100 to everyone on the quiz which consists of 10% of the grade. Mean for Exams are around 50 while first one is 70. He curved the second one because it was really bad(mean around 40). Not sure if he will curve the final raw score for grade cutoff, he previously mentioned he doesn't usually have to make any "artificial modification" to grade(i.e curve). Workload is vary based on your efforts, biweekly quizzes and not graded hw.

Content is relative theoratical. Overall content involves lots of proof and math, it is great if you are into research and wants more theoratical foundation but less emphasis on applied side(more covered in hw but they are not accounted for grade). Lecture is average, he shut you off sometime. It is intimidating to ask questions in the first half as he will make you feel your stupid, but he is more patient and starts explaining more as people asked questions towards the end of the class. He is smart and knowledgable. I put in lots of work for this class and learned considerable amount of stuff. Proceed with cautions if you're thinking taking an easy class, he will make you regret.

optional homework, weekly quizzes. Exams are difficult.

Don't take this class. Egotistic professor. Unhelpful content, poorly explained. No curve

The exams are incredibly difficult (the second exam had a median of 40 before he curved it up a bit) and unlike the content of the class (they are much more theoretical). It is hard to feel prepared for them at all. They are also pretty much the only component of your grade. He curves the class supposedly, but the curve doesn't seem to be very generous either. Lots of people dropped the class right before the drop deadline (after the first two exams), and that presumably would bring the median grade of the class up (since we can assume most ppl who dropped did so because his grading was so harsh they were worried about failing the class or doing very poorly). I asked him if someone who had received grades around the median for the past two exam might still expect to received a B/B+ (what he had said the median of the class usually was curved to) or if they might end up with a lower grade (since being around the median before people dropping would likely mean falling below the median after people dropping), and he just said he can't see the grades of people who drop when grading. I took this to mean the dropped people aren't accounted for int he curve, and therefore, even being around the median most most of the class could lead to a low final grade. It seems that there is no winning in the class unless you are one of the best. If you start in the bottom of the class, you're wo…