Be prepared to spend 20+ hours a week on the homework assignments. I learned a ton from this course. It makes it to where AI/ML is not a black box anymore. You can understand how things are working and how it all comes back to the math.
The lectures are very good. The professor and TAs are very helpful. It is a great course which I would recommend if you are single and have the time.

I don't have anything to say that others haven't already said, Professor Kao is truly one of the best lecturers at UCLA and I would highly recommend this class if you are interested in Neural Networks and Deep Learning. Also, the TAs for this class were amazing, especially Tonmoy Monsoor. Tonmoy is insanely knowledgeable about the topic and his discussions were super useful for the homeworks!

Grading:
Homework: 40% (5 homeworks)
Midterm: 30%
Final Project: 30%
Extra Credit: 0.5% for filling out class eval, up to 1.5% for participating on piazza (in a useful way), and some extra credit given on the midterm (final question on the exam is optional extra credit)

I would highly recommend this class to any interested in deep learning and machine learning. Professor Kao is a very good lecturer and he does an amazing job explaining concepts. I never truly understood how backpropagation worked until he explained it in class. Anyone interested in research/ML should definitely take this class. You will learn so much.

However, the class is not a cake walk. It's actually fairly easy to get a good grade in this class as long as you put in the effort. There is only one exam around week 8, which won't be bad if you pay attention to lecture (our average for the exam was a 95%). The homeworks are the real killer and can take a very long time. You essentially have to build neural networks from scratch using Python and Numpy.

Overall, this is an amazing class where you can truly learn so much, but at the price of many hours of homework. Professor Kao is probably one of my favorite professors I have ever had at UCLA.

This has been my favorite ECE class taken yet and I received my best ECE grade with Kao. The TA was extremely helpful to make this class clear however I think Kao was a big part of making that possible in that he set the precedent of the class to be about genuine learning. I also liked how Kao had a grading scheme where if you did better on the final, it would count for one of the midterms and I think that is what ultimately saved my grade. Overall, great class, especially since fall 2018 was his first time teaching it!

Prof. Kao is, hands down, the best professor I have had in my life. He's extremely smart, engaging, empathic toward students, and generous with grading. His research in neuroscience and the way he demonstrates the overlap with EE and DSP is fascinating and leaves you wanting to learn more.

The class itself is tough, both conceptually and in terms of workload. The homework was manageable, but definitely DO NOT wait until the last day or two. The tests were tough, but the class average was pretty high overall. I highly recommend taking Prof. Kao for any and all classes you can.

I highly recommend taking 102 with this professor. He is very nice and provides many resources to help you out in this class. He went so far as to give our class the midterm and final from last year. (Although the final he gave out this year was a little harder than the one from last year). I particularly like his policy where if you do better on the final than on the midterm, he will replace your midterm score with your final exam score. This ultimately helped me get an A in this class, since I scored a little below average on the midterm but had the time to study really hard for and get a high score on the final.
The structure of his class is excellent overall. He gives challenging but doable homeworks that are really fair; they generally go a bit more in depth than the exams do and help you really learn the material. I recommend trying to do as much of them on your own before turning to your friends and office hours; this helped me gain insight into problem-solving techniques.
All in all, Kao is an excellent professor who is clear, helpful, and wants you to succeed. This has been one of my favorite classes I've taken at UCLA so far, as it's difficult but fair and didactic.

I chose EE as my tech breadth, and I'm so glad I got to take my last class with Professor Kao. He is extremely well prepared in every lecture, and I really liked how he provided an in-depth intuition on all the concepts. Plus, he's really nice! Personally, I found some of his homework to be very hard (took me a couple days), and I had to attend a lot of the TAs' office hours to finish it. However, the midterm and final are around the same difficulty, so if you can do the homework comfortably, the tests aren't a huge worry. I would highly recommend taking this class with Professor Kao!

Kao is an amazing professor! I really like the material of 102, and Kao built it up very naturally - very little felt out of the blue. He explained the material we were learning, stopped for questions, and the name of any student who asked questions or came to office hours. Having a teacher be this invested in a class made it so much easier for me to ask questions and engage with the class - lectures, homework, office hours. He was clear on what we would be testing us on, and his tests were very fair. Office hours were helpful whenever I got stuck on the homework - he basically walks whatever twenty or so students are in his office through some of the problems. One issue I had in another class was the professors office would fill up, but Kao was always accommodating, moving his OH to a larger room when necessary. I would highly recommend taking this class with Kao!!

The material is tough but Kao is a great professor. He does his best to make the lectures clear and engaging and is always open to clarifying questions. It may be hard to pay attention for the entirety of a 2 hour lecture, but I recommend doing your best to take notes. He uploads annotated slides after each lecture that are really helpful if you need to look at examples or study. During lectures he would sometimes have online poll questions for participation points, but more often than not they ended up being cancelled (giving everyone credit) since the strain of the entire class logging in would sometimes freeze the system. Even when they did work, they are graded on participation and not accuracy.

The homework is generally difficult, but there are many resources available to you. For this quarter it was due on 11:59 PM on Fridays. Definitely start it a few days in advance so you can try out the questions and then consult the TAs (during their office hours or discussion sections) or with Kao during his office hours for help with the parts you don't understand. If you aren't able to make it to these, it helps to get to know some of your classmates and check your work with them. The first few homework assignments had MATLAB portions that were a bit tricky, but I was able to complete them with some prior programming experience and a lot of googling.

For the single midterm, a past midterm and a practice midterm were provided as review material, both with solutions. The midterm was intense but fair. I recommend studying the review material so you know what kind of problems to expect, outlining or reading over the slides to ensure you didn't miss any important concepts, and looking over your graded homework assignments so you understand what you missed. For the final, the review material, difficulty, and study methods were similar, though there were a few concepts/problems on it that I didn't anticipate. Not surprising given how many topics this class covers, just try to round out your understanding. The tests are more likely to ask you conceptual problems than the homework.

The tests have an extra credit problem at the end. Usually it doesn't look like the homework problems and it could take you a moment to figure out where to begin; do give them a shot, even a few points of partial credit can help patch holes in your score from elsewhere.

Also be sure to check Piazza if you have any difficulties with the homework or material. Most of the time if you're stuck on a particular problem, somebody has already asked a question about it already. If not, you can submit one yourself. The class was pretty helpful this quarter and the advice given to you is generally enough to nudge you in the right direction.

If you're looking to take ECE 102, Professor Kao is straight up the best professor you can take, and not because everyone else is bad, but because he's SO good. Just in general, nothing in this class was opaque or suspicious, everything has a clear structure and you know the amount of work you have to put in (which is a fair amount).
Professor Kao uses slides, and he annotates them on his iPad, posting both the original and annotated versions on CCLE for you to browse through at your own pleasure. In addition, CCLE also has baseline slides covering all the important topics listed at the beginning of the quarter, so you can get a feel of the different topics that you'd be covering in class. The slides have a clear order, and I must say, are probably the best organized lecture slides I've seen so far. They follow a clear format, doing more than just talking about a theorem to working out an example. He makes lectures engaging by talking about the application and motivation for different topics, why should we learn them, and why they're useful in the real world, and this is pretty important for engineers. Talking about AM radio stations for signal modulation, for example, really gave me an intuition about the purpose of learning signal modulation, and made it much more interesting and engaging to me than just seeing a bunch of equations. He also talks about different learning perspectives, as he draws upon his experiences taking systems and signals during his undergraduate years. You have a 5 minute break in the middle of the lecture (2 hours long), and there's supposed to be an online poll question to check for participation (graded on participation, not accuracy, and counts as extra credit), but given that the website kept on crashing, I think Professor Kao ended up giving everyone credit for participation. The only con against the lectures, which isn't even his fault, is that the room we were in seemed to have no AC, so it was stuck around 95 degrees during the entire quarter.
Make no mistake about it, this class is not easy, and I'd urge anyone to know that "really good" != "really easy class". There are around 7 homeworks in this class, and homework is a big component in the grading scheme (more on that later), so it's important to do well on them. The homework itself is extremely difficult, and time consuming. I'd recommend that you start looking at the questions themselves as soon as possible, and don't be like me and wait until Thursday night (when they're due Friday), since I ended up sleeping at 4-5 am because of this. Try giving the HW problems your best go, and then asking the TAs or your friends, since they can be extremely challenging. The benefit to this, however, is that you will be extremely well prepared for the exams, since he designs the homeworks to be harder than the exams themselves. The midterm (just one) and final are around the same difficulty as the homework (albeit slightly easier), and doing the homework really prepares you pretty well for them. You can be a little strapped for time, but overall, they're not easy, but definitely fair. Each exam has a bonus question at the end, which I'd recommend you at least attempt, because they can help if you lose points elsewhere, and generally Jonathan and the TAs are not extremely strict graders.
For administrative matters, this class is graded on the following: 30% HW, 30% Midterm, 40% Final, with an additional 2.5% in extra credit available (I believe 0.5% for instructor evaluation, 0.5% for participation, up to 1.5% for participation in Piazza). Kao also utilizes a straight scale, so no curving, but he does compensate by lowering the grade boundaries depending on how everyone does for the exams (for us, 92 and up was an A, 89 and up a A-, etc.). He also has a policy where if you do better on the final than the midterm, the final can replace the midterm grade, which he says is because his professor made him that same offer when Kao was an undergraduate, which I find to be extremely considerate of him. All homework assignments and exams are uploaded to Gradescope, so it's really easy to see how you did and where you lost points and where to improve. While I couldn't make it to his office hours, I've heard from my friends that he's really helpful and nice, and this is evident because he remembers students names when they answer questions during lecture, depending on if they've shown up to his office hours before.
Even after all that, it's the little things that make this dude the best professor to take systems and signals with. For example, on Thanksgiving holiday, he gave us an extra two days to do the homework (due Wednesday before Thanksgiving), and posted the next homework after Thanksgiving day. When we had lecture cancelled due to the wildfire, he sent the class a YouTube link of the same lecture from last year, and when students were struggling with sampling, Professor Kao sent a YouTube lecture for further help on sampling, which shows how dedicated he is to making sure that students are grasping the concepts. He'll even check during lecture, asking for a show of hands to make sure that people are following, or else he'll stop to take more questions. It's the little things as well that makes this such a great class to take, and I'd wholly recommend Professor Kao. If offered the chance I'd take him again and again for systems and signals.