You DON'T need my permission and can do it online by yourself.
We aim to learn optimization methods and implementations for deep learning. Thus if you only would like to use deep learning for applications, this is not a course to take.
We focus on the algorithms, their implementations, and their practical use.
In a way you can think that we position ourselves as those who write optimization implementations in existing deep learning tools.
Clearly, the design of this course is related to my past experiences on applying optimization algorithms on other machine learning methods. For example, we developed the widely used SVM package LIBSVM
Please check the course web page.
The easiest way to find the course page is to search my name. On my homepage there is a section "Courses." It's listed there.
You should have basic understanding of the two areas optimization and deep learning. However, I don't expect you are an expert on these areas.
It's not clear yet at this moment. Things depend on
We will use NTU COOL system for your project submission (see URL here. This place is only used for submitting reports/slides). No late submission will be accepted.
One or two pages (including references). Use the latex template here. See the resulting pdf. The template is based on Yinxue Xiao's first project report at UCLA in 2019. For final project, you should use the same format, but there should have no page limit.
Please submit one pdf file only. No other files. No sub-directories.
You get zero point.
When using outside resources, proper citation is necessary. This includes papers, text books, software libraries, websites, and helps from others.
Discussion is perfectly fine.
Please state what you have done. No fake results and no exaggeration. For doing research, failure is an option
For every project you will get a score. In the end we do a weighted average.
For the project report you must pay attention to the writing and the organization. For a badly written report, no matter how great your results are, you get a low score.
Depending on your performance, we decide the distribution of your grades. That is, how many get A+ and how many get F-. Then, we calculate raw scores, obtain a ranking of students, and assign their grades.
So there is no direct relationship between your raw score and your grade. It is possible that your raw score is 99, but you get F-.
Very heavy. This course is expected to take 1/3 or more of your time spent on taking courses
We assume that you can find computing resources needed for your projects
No, you can use whatever you like. However, from experiences in the past we strongly suggest you to use linux.
Please email me. Any improvements on slides will be useful to students in the future.
Yes, absolutely.