You are currently browsing the category archive for the ‘Teaching’ category.

Taesik (my husband and a colleague in the Industrial & Systems Engineering Department) teaches a graduate course on health care delivery. Part of that course discusses health information, such as Electronic Health Records, Personal Health Records, and online health information. I volunteered to give a lecture on health information on the Web: what the current status is, what improvements can be made so that users can get better health information from the Web, and how some computational methodologies can be applied to health information on the Web.

I did this in part because Taesik is suffering from a wisdom tooth extraction procedure, and it was a win-win-win situation. I gave him a couple of days to recover from the operation without having to give a lecture. I had a good time preparing for and delivering the lecture, and at the same time, I got to organize my thoughts about applying the ideas and methods used in our lab to health information. And I think, for the most part, students appreciated this change of perspective, from a systems engineering point of view to a computer science point of view.

I spent quite a long time preparing the presentation, so I want to share it with everyone here. Note that it is not a very technical talk. It’s intended to serve a general audience.

The Social Web and Health Information: A Computational Perspective

Advertisements

With Kim Yu-Na becoming an Olympic champion, the whole country is focused on her gold medal. She certainly is an extraordinarily gifted and hard-working young woman and deserves all the credit and more. However, as an educator, I cannot help but wonder how her coach brought out the best in her. Is it by giving encouraging words? Is it constant tips, techniques, demonstrations of the skating skills? Is it genuine love and care? Is it about setting high expectations, realistic goals, and everyday reminders of the goals and expectations?

During the Olympics, Yuna’s coach and Mao’s coach, their faces showed different emotions. I think that it was not just because of the differences in Yuna and Mao’s performances at the Olympics. I think their faces reflected the very different styles of coaching.

As for me, my biggest concern is finding my coaching style. Research is hard, but advising students is much much harder.

It is also much more rewarding.

In fact, when I was a PhD student, I did not think much about a career in academia. I somehow stumbled upon this profession, but now I am very glad that I am a professor in a research-oriented university with many opportunities to advise graduate students.

For the most part, the results of our research do not make big impacts in the real world, but advising students can and do make big differences.

I try to talk to other faculty to get advice on advising students. But there seems to be no right answer. Every student is different, every advisor is different, and every interaction is different. There seems to be no way to get a training set and expect it will be from the same distribution as the testing set. Nevertheless, learning must occur. How???

Fortunately, we have intelligence that does not rely solely on statistics. You just take on each interaction with each  student, try the best you can, and hope to get some positive results.

And with experience, I hope, I will get better with those interactions. I am not sure, though, whether I will ever feel qualified to be their role model. For that, I will have to try harder. Anyway, for now, every day is a struggle just to make sure I do not make unrecoverable mistakes.

Of course, I enjoy it immensely!

Today I am thinking about the graduate-level AI course I will be teaching next semester. This post is mainly for my own reference. I just want to store all the good course material I find in one place. The textbook I will use is the ever-famous AIMA (Artificial Intelligence: A Modern Approach) by Russell & Norvig. It is, as far as I know, the most widely-used AI textbook, and it is well-written.

I hesitated about posting the course websites here, lest students find them and somehow “cheat”. However, after thinking just for a few seconds, I decided not to worry. If they are diligent and interested enough to actually look at the course material in advance, all the better! I don’t have to teach them because they can learn from these other courses on the web! I just have to be careful not to assign homework or exam problems that have solutions on these webpages.

Many thanks to the instructors of these courses. I selected mainly US university courses published in the last couple of years.

Brown University, Spring 2008

UC Berkeley, Fall 2007

UC Berkeley, Fall 2008

CMU, Spring 2007

Georgia Tech, Fall 2007

Harvard, Fall 2008

UIUC, Spring 2007

For the last three days, I participated in the admissions interviews for KAIST. During the whole process, the question that’s been bugging me was, “what kind of a student body do we want?” By “a student body”, I mean the total distribution and population of undergraduate students in terms of their intellectual capacity, curiosity, diligence, academic rigor, talent, passion, and personality.

The format of the interviews–group discussion, individual q&a, 5-minute speech–all seem to favor those with good public speaking skills. But these students, coming from an educational system based on reading, writing, and working on math and science problems on paper, are not accustomed to public speaking, especially in front of professors. The Admissions Office has decided on this interview format because they wanted to recruit students who will become future leaders in science and engineering. I agree wholeheartedly that public speaking skills, along with other leadership skills, are important for future S&E leaders, but still, I could not resist sympathizing with these seventeen-year-olds who were just not trained to speak up. We, the interviewers, were supposed to rate the students on their creativity, thoughtfulness, attitude, and other subjective metrics that were not shown on their school records, but in many cases, I felt the students probably possessed many of these qualities but just could not express them because they were so nervous.

The other professor in my room, who is probably in his late 50s or early 60s, expressed a similar viewpoint several times during the three days. He wanted to give everyone a chance to study at KAIST. I agree with him. After all, these are seventeen (some are sixteen) year-olds who have been working so hard to get into KAIST. I felt that most of the students had plenty of potential to become great leaders, if they are trained well at KAIST. Of course, there is only a limited number of students we can accept each year, but I want to congratulate each and every student who came into our room, “GREAT JOB!”

I both fear and look forward to my first semester of “real” teaching.

I am teaching 1.33 courses next semester. The “1” is for a graduate AI course, and the “.33” is for an advanced undergraduate course that I am co-teaching with two colleagues. I have been thinking about the .33 course lately because we are drafting a course outline for it. The course will be called something like “CS and Probability” or “probabilistic (statistical?) methods in CS”, and as the name suggests, will cover probabilistic (statistical) methods used in solving problems in computer science. We decided to offer this new course because we felt the undergraduates needed a fun introduction to some of the current topics in AI research. (I know that the title does not sound very fun.)

My part of the course will be on statistical NLP. I plan to introduce some interesting problems in natural language processing, present a few empirical approaches, and have the students implement some of the well-known algorithms. There are two nice courses at CMU that I will use as references, though those courses, spanning 2 semesters for master’s level students, cover much much more than I will attempt. Thanks to Roni and Noah for the valuable course material.

Language & Statistics

Language & Statistics II