- Home
- Search
- Adnan Darwiche
- COM SCI 161
AD
Based on 23 Users
TOP TAGS
- Would Take Again
- Tolerates Tardiness
- Is Podcasted
- Engaging Lectures
- Appropriately Priced Materials
- Often Funny
- Issues PTEs
Grade distributions are collected using data from the UCLA Registrar’s Office.
Grade distributions are collected using data from the UCLA Registrar’s Office.
Grade distributions are collected using data from the UCLA Registrar’s Office.
Grade distributions are collected using data from the UCLA Registrar’s Office.
Grade distributions are collected using data from the UCLA Registrar’s Office.
Grade distributions are collected using data from the UCLA Registrar’s Office.
Grade distributions are collected using data from the UCLA Registrar’s Office.
Grade distributions are collected using data from the UCLA Registrar’s Office.
Grade distributions are collected using data from the UCLA Registrar’s Office.
Grade distributions are collected using data from the UCLA Registrar’s Office.
Sorry, no enrollment data is available.
AD
TAKE HIS CLASS! Professor Darwiche is an absolute gem! I got into the class on a last-minute PTE after spring quarter went remote. He has to be one of the most well-adjusted professors out of all of UCLA's remote courses.
From day one, he has been prepared and well-versed with the Sketchbook app to use as a whiteboard (great handwriting too), rarely had tech problems, edited *ALL* of the recorded lectures to correct mistakes on screen and cut out any pauses/wait time. He divided the videos into 2 parts to upload, each 35-40 minutes long, which made it super easy for us to find things when rewatching. Even went to lengths to add his own intro music for the videos and sometimes draws a little daisy on the first slide :')
He always stuck around after lecture to answer students' questions and provided external resources (optional) if you were interested in reading more. He's very patient, used engaging and funny examples, and explained concepts SO well. This was not a class where I had to often re-watch lectures or read the textbook to catch up.
Exam was open book and pretty manageable, exactly what you'd expect based on lecture and homework material. TA's were also very knowledgeable and helpful in discussion (Shirley was great!) There's roughly one homework per week, usually takes less than 4 hours.
I already knew Darwiche was a beloved and highly-regarded professor before enrolling his class, but in contrast to how other professors are handling remote instruction, Darwiche is miles ahead and definitely went above and beyond to make sure students are getting the best out of this course. Really wish I can take another class with him some day!
This is a great CS elective - fairly easy to get an A in, but not trivially easy. It provided a great high-level overview of AI and its applications, but note that it never delved into the details. Taking this online during Spring 2020, I found that online lectures + piazza were actually more helpful than in person lectures, so I appreciate Darwiche's adjustment to unusual circumstances this quarter.
I recommend the CS 131 + CS 161 combo highly, the logic + Lisp learned initially in CS 161 (at a manageable pace) was really helpful for Prolog and Scheme in CS 131 (learned at a breakneck pace), considering Eggert barely teaches anything.
The projects take time, but nowhere near CS 131. Also, the specs are very specific and (mostly) clear, and the Piazza is helpful; hence, while the projects probably take 5-15 hours a week, it's usually closer to ~7, in contrast to the 20-40 hrs/week for CS 131 projects.
Exam advice: We had mostly MCQ questions and an online format for Spring 2020. So I can't really speak to that. But they weren't trivial, although we learned everything in the exams, unlike an Eggert exam.
Final thoughts: Great CS elective with Darwiche, makes sense why it fills up so fast. Learned Lisp, and basic principles in AI, but didn't learn a huge amount regarding ML / AI (aka, not as much as I had hoped). However, this is due to the workload not being too bad, which is good. 5/5 but don't expect a great intro the AI/ML in regards to knowledge; more of a class to pique interest in the field. But not a trivial amount of work, some of the projects take a decent amount of time.
His lectures were great. He would go into great detail for all the material to make sure we all understood what was going on.
First couple of weeks he taught Lisp. Then for a big chunk of the course, we learned about search algorithms (BFS, DFS, IDDFS) and heuristic algorithms (A*) among other types of algorithms. Last portion was about probabilities and Bayesian networks. All the homeworks built off of these topics. You end up coding most of these algorithms, which I think was a good experience.
The exams were fair. You could read the book, but usually just noting what he covers and emphasizes in class is sufficient.
Overall: good experience, would recommend.
Professor Darwiche is a really thoughtful guy. He recorded all lectures and would spend all day editing them (with his own intro music that we different every week!). He usually started off lectures by listing what we're covering that day and summarizes everything at the end too. He periodically checked the Zoom chat for questions and would answer them. He also stayed after lectures for a few minutes to answer any questions.
I sometimes got lost in the class because I wasn't sure what the big idea he was talking about was and would feel confused on how it connected to the rest of the content but maybe that was just me.
My TA Jinghao was really good. His slides were really clear and explained everything in a simple way.
Also, this is my own observation and I'm not sure if other people in my class felt the same but I noticed that some of the concepts he taught weren't easy to find online. And whenever you did find something, it was always his papers. So that makes me wonder how widely used that stuff is in the "real world".
There wasn't a need for a textbook or anything. Homeworks are your standard CS projects so you should expect to put some work into them. They helped me understand some of the concepts more but there were about 2-3 of them that I just couldn't wrap my head around. Tests were less complicated than I expected to be honest. The final was 60 multiple choice and T/F questions which were very conceptual. Median was like 79 for it.
The professor is one of the most caring I’ve ever had. Every lecture is meticulously prepared, with diagrams and data prepared in a neat folder on the professor’s computer and pasted into the lecture (digital) whiteboard when needed. He is also quite passionate about certain aspects of course that relate to his own research, which is always great to see in a professor. Course materials and homeworks are also well prepared and interesting.
I'm so glad Professor Darwiche decided to become a Professor. I just wish he taught more CS classes; I would take them all. He is kind, patient, clear, and knowledgeable. I learned a tremedous amount in his class (and not just retaining the information long enough to get a decent grade).
Make every effort to take his class, even if you're not interested very much in AI. I can't remmeber one lecture where the classroom wasn't packed. If you're a CS major, you know how rare that is. He's just that good.
Adnan is one of the best professors at UCLA. Really, this man makes me feel proud of being a UCLA student. For once after 3 years I don't look at Youtube videos of other universities and feel that I'm missing out a lot by not going to MIT or Stanford.
I wish this class would continue on to AI 2 and AI 3 as a whole year program. Adnan should basically teach anything remotely related to AI and algorithms. He simply breaks down everything to conceptual understanding of the material rather than regurgitating some mathematical notation and call it a day.
This class was a lot of fun for me. You have to still work pretty hard for an A but the exam and assignments are fair.
His enthusiasm for teaching the subject and his energy during the lecture is contagious. It's really hard to fall asleep during his lecture.
I highly recommend this professor.
Professor Darwiche is great! He's an engaging professor and the projects are interesting and fun. His tests are also fair and he makes an effort to make sure the material is understandable. The course covers a broad range of AI topics and gives a good overview of the field.
TL;DR Class is very slow paced. I wish there would have been more of the interesting material and less alphabet soup and symbols to memorize.
First few lectures are on Lisp, which is very easy, but also pretty much immaterial to the actual meat of the class (nothing you do in lisp couldn't be done EASILY in the other languages we learn as CS majors). I'm guessing they do it this way so grading is easier since the class is relatively popular. Also, they limit how much of the language you are allowed to use in the projects which is odd.
The next part is on Search and 2 player games, but the interesting part of Search (A*) was unsatisfyingly short for me. For 2 player games, you really only learn the simplest version Alpha-beta (and do no projects on it), which is a highly shortened treatment of a very interesting subject in my opinion.
You then cover SAT-Solving, which was interesting, but the project was just an N-Queens in Lisp which reduced to basically just translating a loop, and didn't require any of the techniques previously described in the class except depth first search ($10 says a solution that just returns precomputed solutions for the first 50ish problems would get full credit).
The last part of the class is Bayesian networks, which was probably given too high level a treatment. The problems we had to solve with it we were given software for, so I don't feel this was effective for teaching me.
You might think that given what I've said above, that I didn't like this class. That isn't quite true. I overall enjoyed it, but I feel it could have been a lot more.
Adnan, if you see this, here are my suggestions.
1.) Open up the allowed language list. It will make grading trickier, but will also let you spend more time on important material.
2.) Spend more time on A* and SAT and less time on the "dumb search" techniques (BFS etc)
3.) Spend more time on "game AI". Alpha-beta is one algorithm, but Monte Carlo Search with Upper Confidence Bound is a another one that is very interesting (popularized in 2006! and performs much better than Alpha-beta for certain games). I'm of course not an expert in this field, but there's a lot of interesting things that could be explored here
4.) Go a little deeper on Neural networks and the algorithms they use. It was too high level to be useful to me in my opinion. Consider having us implement one of the algorithms instead of just trying to figure out the SamIAm gui for a project.
I know AI has a large breadth as well as depth, but I still find the lack of depth in this class disappointing.
TAKE HIS CLASS! Professor Darwiche is an absolute gem! I got into the class on a last-minute PTE after spring quarter went remote. He has to be one of the most well-adjusted professors out of all of UCLA's remote courses.
From day one, he has been prepared and well-versed with the Sketchbook app to use as a whiteboard (great handwriting too), rarely had tech problems, edited *ALL* of the recorded lectures to correct mistakes on screen and cut out any pauses/wait time. He divided the videos into 2 parts to upload, each 35-40 minutes long, which made it super easy for us to find things when rewatching. Even went to lengths to add his own intro music for the videos and sometimes draws a little daisy on the first slide :')
He always stuck around after lecture to answer students' questions and provided external resources (optional) if you were interested in reading more. He's very patient, used engaging and funny examples, and explained concepts SO well. This was not a class where I had to often re-watch lectures or read the textbook to catch up.
Exam was open book and pretty manageable, exactly what you'd expect based on lecture and homework material. TA's were also very knowledgeable and helpful in discussion (Shirley was great!) There's roughly one homework per week, usually takes less than 4 hours.
I already knew Darwiche was a beloved and highly-regarded professor before enrolling his class, but in contrast to how other professors are handling remote instruction, Darwiche is miles ahead and definitely went above and beyond to make sure students are getting the best out of this course. Really wish I can take another class with him some day!
This is a great CS elective - fairly easy to get an A in, but not trivially easy. It provided a great high-level overview of AI and its applications, but note that it never delved into the details. Taking this online during Spring 2020, I found that online lectures + piazza were actually more helpful than in person lectures, so I appreciate Darwiche's adjustment to unusual circumstances this quarter.
I recommend the CS 131 + CS 161 combo highly, the logic + Lisp learned initially in CS 161 (at a manageable pace) was really helpful for Prolog and Scheme in CS 131 (learned at a breakneck pace), considering Eggert barely teaches anything.
The projects take time, but nowhere near CS 131. Also, the specs are very specific and (mostly) clear, and the Piazza is helpful; hence, while the projects probably take 5-15 hours a week, it's usually closer to ~7, in contrast to the 20-40 hrs/week for CS 131 projects.
Exam advice: We had mostly MCQ questions and an online format for Spring 2020. So I can't really speak to that. But they weren't trivial, although we learned everything in the exams, unlike an Eggert exam.
Final thoughts: Great CS elective with Darwiche, makes sense why it fills up so fast. Learned Lisp, and basic principles in AI, but didn't learn a huge amount regarding ML / AI (aka, not as much as I had hoped). However, this is due to the workload not being too bad, which is good. 5/5 but don't expect a great intro the AI/ML in regards to knowledge; more of a class to pique interest in the field. But not a trivial amount of work, some of the projects take a decent amount of time.
His lectures were great. He would go into great detail for all the material to make sure we all understood what was going on.
First couple of weeks he taught Lisp. Then for a big chunk of the course, we learned about search algorithms (BFS, DFS, IDDFS) and heuristic algorithms (A*) among other types of algorithms. Last portion was about probabilities and Bayesian networks. All the homeworks built off of these topics. You end up coding most of these algorithms, which I think was a good experience.
The exams were fair. You could read the book, but usually just noting what he covers and emphasizes in class is sufficient.
Overall: good experience, would recommend.
Professor Darwiche is a really thoughtful guy. He recorded all lectures and would spend all day editing them (with his own intro music that we different every week!). He usually started off lectures by listing what we're covering that day and summarizes everything at the end too. He periodically checked the Zoom chat for questions and would answer them. He also stayed after lectures for a few minutes to answer any questions.
I sometimes got lost in the class because I wasn't sure what the big idea he was talking about was and would feel confused on how it connected to the rest of the content but maybe that was just me.
My TA Jinghao was really good. His slides were really clear and explained everything in a simple way.
Also, this is my own observation and I'm not sure if other people in my class felt the same but I noticed that some of the concepts he taught weren't easy to find online. And whenever you did find something, it was always his papers. So that makes me wonder how widely used that stuff is in the "real world".
There wasn't a need for a textbook or anything. Homeworks are your standard CS projects so you should expect to put some work into them. They helped me understand some of the concepts more but there were about 2-3 of them that I just couldn't wrap my head around. Tests were less complicated than I expected to be honest. The final was 60 multiple choice and T/F questions which were very conceptual. Median was like 79 for it.
The professor is one of the most caring I’ve ever had. Every lecture is meticulously prepared, with diagrams and data prepared in a neat folder on the professor’s computer and pasted into the lecture (digital) whiteboard when needed. He is also quite passionate about certain aspects of course that relate to his own research, which is always great to see in a professor. Course materials and homeworks are also well prepared and interesting.
I'm so glad Professor Darwiche decided to become a Professor. I just wish he taught more CS classes; I would take them all. He is kind, patient, clear, and knowledgeable. I learned a tremedous amount in his class (and not just retaining the information long enough to get a decent grade).
Make every effort to take his class, even if you're not interested very much in AI. I can't remmeber one lecture where the classroom wasn't packed. If you're a CS major, you know how rare that is. He's just that good.
Adnan is one of the best professors at UCLA. Really, this man makes me feel proud of being a UCLA student. For once after 3 years I don't look at Youtube videos of other universities and feel that I'm missing out a lot by not going to MIT or Stanford.
I wish this class would continue on to AI 2 and AI 3 as a whole year program. Adnan should basically teach anything remotely related to AI and algorithms. He simply breaks down everything to conceptual understanding of the material rather than regurgitating some mathematical notation and call it a day.
This class was a lot of fun for me. You have to still work pretty hard for an A but the exam and assignments are fair.
His enthusiasm for teaching the subject and his energy during the lecture is contagious. It's really hard to fall asleep during his lecture.
I highly recommend this professor.
Professor Darwiche is great! He's an engaging professor and the projects are interesting and fun. His tests are also fair and he makes an effort to make sure the material is understandable. The course covers a broad range of AI topics and gives a good overview of the field.
TL;DR Class is very slow paced. I wish there would have been more of the interesting material and less alphabet soup and symbols to memorize.
First few lectures are on Lisp, which is very easy, but also pretty much immaterial to the actual meat of the class (nothing you do in lisp couldn't be done EASILY in the other languages we learn as CS majors). I'm guessing they do it this way so grading is easier since the class is relatively popular. Also, they limit how much of the language you are allowed to use in the projects which is odd.
The next part is on Search and 2 player games, but the interesting part of Search (A*) was unsatisfyingly short for me. For 2 player games, you really only learn the simplest version Alpha-beta (and do no projects on it), which is a highly shortened treatment of a very interesting subject in my opinion.
You then cover SAT-Solving, which was interesting, but the project was just an N-Queens in Lisp which reduced to basically just translating a loop, and didn't require any of the techniques previously described in the class except depth first search ($10 says a solution that just returns precomputed solutions for the first 50ish problems would get full credit).
The last part of the class is Bayesian networks, which was probably given too high level a treatment. The problems we had to solve with it we were given software for, so I don't feel this was effective for teaching me.
You might think that given what I've said above, that I didn't like this class. That isn't quite true. I overall enjoyed it, but I feel it could have been a lot more.
Adnan, if you see this, here are my suggestions.
1.) Open up the allowed language list. It will make grading trickier, but will also let you spend more time on important material.
2.) Spend more time on A* and SAT and less time on the "dumb search" techniques (BFS etc)
3.) Spend more time on "game AI". Alpha-beta is one algorithm, but Monte Carlo Search with Upper Confidence Bound is a another one that is very interesting (popularized in 2006! and performs much better than Alpha-beta for certain games). I'm of course not an expert in this field, but there's a lot of interesting things that could be explored here
4.) Go a little deeper on Neural networks and the algorithms they use. It was too high level to be useful to me in my opinion. Consider having us implement one of the algorithms instead of just trying to figure out the SamIAm gui for a project.
I know AI has a large breadth as well as depth, but I still find the lack of depth in this class disappointing.
Based on 23 Users
TOP TAGS
- Would Take Again (7)
- Tolerates Tardiness (3)
- Is Podcasted (4)
- Engaging Lectures (7)
- Appropriately Priced Materials (2)
- Often Funny (4)
- Issues PTEs (2)