Peter Belhumeur

Prof. B has a lot of knowledge in computer vision. Great guy and funny one as well. Like the previous reviews, this class was a chill class but the first two assignments were a little hard because I never took an Aj/ML course before hand. All the things you need to know are on the slides and its mostly integrating math equations into code for the first couple assignments. Lots of freedom in this class for the group project + you can choose your teammates/go solo.

Seminar course with approximately 20 students, mostly graduate students. Belhumeur is very chill and makes it clear that this class is all about producing a mobile app to be presented at the end of the semester. He proposed a couple of ideas related to his own research (extending the BirdSnap iPhone app developed in his own lab, or another app related to to identifying birds by their calls). Most students (usually working in pairs or groups of 3), came up with their own ideas, involving some elements of CV or ML topics in their app. For the first half of the semester, each class period was split half and half in terms of CV/ML lecture from Prof. Belhumeur, followed by a guided tutorial to iOS app development led by the TA, Michael Yang (who was excellent). About halfway through the semester, we moved away from this format, and basically started demoing the progress that each group had made. Overall a fun and low-stress class, where you have a ton of freedom to be creative and explore new CV/ML methodologies. Some mobile dev knowledge is preferred (you can do either iOS or Android, doesn't matter), but most of the class was pretty new to mobile development and learned things as they went. In the end, most of the actual work happens server side, so your mobile app's frontend will likely be fairly rudimentary.

Biometrics boils down to 1) [Image Processing] feature extraction that gathers information (face shape) from raw data such as images (male/female jpgs) and 2) [Machine Learning] An algorithm that takes info from 1) and classifies the raw data (im1.jpg = male etc.) I'm not going to recommend this course for the following reasons: 1) The meat of the theory can be described in the rest of the review text to a cs junior. I do not believe a 3 credit course with all those lecture hours should be this shallow. 2) This course doesn't teach you any engineering skills. There is no critique on programming style and you're expected to learn MATLAB (3 hrs) on your own. The code that you write, including the final project, are toy programs averaging 80 lines of code. The algorithm itself is only 10-20 lines of API calls, the rest is I/O. 3) No theory behind Image processing is covered, basic API calls are provided in the skeleton code for the assignment. PCA and Fisher analysis is discussed but this is 3 lectures at most. 4) DO NOT take this course for Machine Learning. Bayes' theorem (which bag did the red ball come from?) and a baby algorithm (intimidatingly called "K-nearest-neighbors) are all the tools you learn. SVMs are discussed for culture.

I got in the habit of showing up 10-20 minutes late for every class and was hardly ever late. Additionally, it was not uncommon for class to get out rather early. While Professor Belhumeur is occasionally remarkable in his nonchalance, he is one of the friendliest CS professors I've had and actually does, somehow, manage to get through all the material in a concise manner. He does put effort into insuring that students understand the material and getting student feedback about homework difficulty and other concerns.

This course was wack. Despite the class having 85 students, Prof. Belhumeur insisted that it was supposed to be a seminar. Every week, the prof picked a topic, and 4 students had to volunteer to present papers that were related to said topic. Since the class was 2 hours long, each student was originally supposed to present 2 papers in 15-20 minutes. However, the presentations always went on too long, causing a huge backlog early on that we never recovered from. As a result, we never got to the second half of the topics, and some students were never able to present. This brings me to my main complaint about the class: Prof. Belhumeur doesn't do anything. He mostly sits back and expects students to run the class for him. This would be understandable for a traditional seminar, but it's just not feasible for every student to be able to present when the professor isn't even moderating the presentation times appropriately. You'd think that this wouldn't be a big deal, but this became a serious issue when final letter grades came out (more on that later). It doesn't help that he's notorious for ignoring emails and Slack messages, so most communication is with the TAs instead. In addition to student presentations, there was also a semester long project to be done in groups of 1-4. Based on my experience, the grading for these projects was also ridiculously inflated like it was in Prof…

Prof. Belhumeur is totally chill, but definitely here to do research and not to teach. He came to Columbia from Yale a couple of years ago, and yet he still doesn't know how the credit system here works. He's invariably 5 to 10 minutes late, and he has missed 3 or 4 classes. He did a few useful grounding lectures in the beginning, and then mostly took a back-seat role, letting students present and commenting occasionally. He is very nice and approachable, but only when you can get hold of him--as big shot like Nayar, he is often away on conferences and things. Overall a nice person and okay teacher for the self-motivated.

6 programming assignments + 1 project. Project is very involved and great opportunity to do good work.

He is awesome. Great guy. Actually talks to the class and engages us in conversation. Midterm was easy and he posts sample solutions for problems very similar to the homework problems. You'll want to take any class with this guy.

Peter's a chiller. Doesn't seem to be that into teaching but he knows a ton about deep learning. Good class to take if you already know something about deep learning or are looking for a gentle introduction to the field. Not a great class if you want something super rigorous. The project is extremely open-ended so if that's your style then this is the class for you.

As much as you want it to be. Your grade is determined from participation (it is a seminar/discussion based class after all, so provide critiques and comments on others' ideas), and your final app + presentation/summary report. It would be smart to have your app mostly functional a couple weeks before the end of the semester so you aren't rushing to finish it on top of the millions of other projects you'll be dealing with at the end of the semester :)