Update June 2 2021: click here for my acceptance speech (in Korean only)
Note: This is the first in a series of up to three posts related to the Ho-Am Prize I was awarded this year.
- Ho-Am Prize & Scholarship for Macademia at Aalto University
- Ho-Am Prize & 백규고전학술상 (Baek-Gyu Scholarly Award for Classics)
What an honour it has been to be a recipient of the Samsung Ho-Am Prize in Engineering this year (2021)! The Ho-Am Prize is one of the biggest and perhaps most recognized awards in Korea. Quoting the Ho-Am Foundation directly:
The Prize is presented each year to individuals who have contributed to academics, the arts, and social development, or who have furthered the welfare of humanity through distinguished accomplishments in their respective professional fields.
In particular, the Ho-Am Prize in Engineering is awarded to “people of Korean heritage whose accomplishments have contributed to the development of industry for greater prosperity for humanity.“
I’m quite certain what i’ve done so far is anything remotely close to contributing to either the development of industry or greater prosperity for humanity. but, i take it that this Prize was awarded to me not for my individual achievement but to recognize “what we have been able to collectively achieve over many decades in the field of deep learning and more broadly artificial intelligence and data science.“*
regardless of whether the Prize celebrates my own achievement or the set of achievements we have made collectively, it turned out that i am the one who receives “cash prize of KRW 300million (approx. 275,000 USD)“. I KNOW! this is the biggest cash prize i’ve ever received. in fact, i could even say this is by far the biggest chunk of money i’ve received at once, and the second largest one does not even come close to it.
since i take it that this Prize recognizes our field rather than myself as an individual, i’ve decided to use this enormous cash prize not for myself but to serve a broader society. because it’s a pretty hefty prize, i’ll spend it in 2-4 distinct ways over the next few months, and in this post, i’ll share with you my first attempt at giving away this cash prize.
one of the most fortunate moments in my career so far was one day in Fall 2008. my friend (Yongwook) and i were taking a course designed for freshman students in a non-computer science major, when both of us were very, very, very far from our freshman years. perhaps obviously, we were always sitting at the very back of a large lecture hall with the sole goal of finally graduating from the university at some point. one day, Yongwook showed up a bit late, rushed into the lecture hall and sat down next to me. he then showed me a (possibly the ugliest) brochure he picked up in front of the department office on his way to the lecture hall. it was a brochure sent to KAIST Computer Science by Aalto University (back then Helsinki University Technology) about the (relatively) new international master’s program in machine learning and data mining. the program was named “Macadamia” (no idea where the final “a” comes from.)∘
until then, i never planned to continue my study beyond my undergraduate degree, i never thought of going abroad for studying further, and i never even imagined moving to Finland. but, somehow, there it was: the pamphlet from Finland, telling me about this master’s program in machine learning and data mining. within a few months, i was on a Finnair flight on my way to Helsinki (though, i’ve never “lived” in Helsinki but only in Espoo ever.) and, until now, this was one of the best decisions, if not the best one, i’ve ever made in my whole life.
i still cherish the years i spent in Finland.
Internationalization and representation
internationalization matters. just by talking with, hanging out with and just simply listening to people from all over the world, we not only learn how others live, but we ourselves live, experience, understand and accept how others live all over the world. in doing so, we become more tolerant and open-minded. so, yes, internationalization matters, and we must strive to actively create an environment in which no group of people is marginalized and in which everyone is welcome and can interact with each other.
representation matters. representation matters from at least two aspects. first, representation self-reinforces. for instance, it’s quite difficult for me to imagine my little niece dreaming of becoming an AI researcher, because it’s not easy for me to see how she would find the field of artificial intelligence welcoming, when the whole field is pretty much dominated by men. the only way to break this is to make sure all, truly all, are represented. second, representation is a path toward safety, equity and fairness in engineering and science. i might sound a bit like a broken record at this point, but for instance quite a bit of issues arising from deploying AI/ML systems could have been caught before their deployment had those systems been developed and vetted by a team of developers that properly represent the diversity of the society (see here for a few examples and pointers to original sources.) so, yes, representation matters in ensuring safe, equitable and fair development and deployment of systems we build.
compared to my experience prior to joining Aalto University back in Korea, Aalto University provided me an environment which were much better internationalized and had generally better representation across various aspects. this greatly helped me broaden my view and perspective on a diverse set of topics, and really changed how i perceive the world in general. looking back however i must unfortunately say that my bar was very low.
Aalto University, and the Finnish society more broadly, also suffers from the (relatively) lack of internationalization and diversity. i was in the “international” master’s program which was taught (almost) entirely in English (if i recall correctly Finnish 1 was required, which was perhaps unsurprisingly in the mix of English & Finnish) and attracted talents from all over the world. indeed in my cohort, if i recall correctly, either all but one or all my peers were from abroad, which allowed me to interact with them, learn from them and become a friend with them. however, outside this program, along with a few other international master’s programs, it was a reasonably rare sight to find non-Finnish students at Aalto University (well, at least in the School of Science and Engineering, back then.) there were certainly more non-Finnish but European students who were spending their exchange years, although they weren’t too many either.
Furthermore, within my cohort of Macadamia, if i recall correctly, there was one female student out of 12 or so students.# this balance seems particularly bad, but the balance wasn’t too good among students as well as faculty members within general computer science. i have no statistics available in my hands now, but my personal experience tells me that gender balance was definitely better at Aalto CS than at KAIST CS where i studied computer science in my undergrad years. this however did not mean that it was any good at Aalto CS, but just that my bar was very low.
as i’ve explored beyond Finland, i’ve seen, experienced and enjoyed places that are more internationalized and have more balanced representation of a diverse population. Aalto University can and should do better to better serve its students as well as Finland and more broadly the world by further improving its internationalization and building an even more diverse campus.
Scholarship for non-EU, female students
here’s two sides of my feeling toward Aalto University:
- my experience at Aalto University and Finland was simply amazing, and i want to contribute to making this experience available to a broader group of students from all over the world.@
- Aalto, and more broadly Finland, could benefit even more from having a more diverse set of students so that the whole society, and its members, continue to stay (and become even more) open-minded and tolerant.
these are not mutually exclusive nor mutually independent. in fact, one may say that these are essentially the same thing.
to this end, i’ve decided to donate €30,000, using the prize from the Ho-Am Award, to Aalto University School of Science with a condition that this is used to support female students from non-EU countries who are entering the Macadamia program.$ Similarly to my earlier donation to Mila, i’ve asked Aalto University to provide one-time supplement of €1,000 each to approximately five such students each year. See here for the official announcement from Aalto University.
this is my small gesture of thanking them for coming to Aalto University and Finland to study, which in turn improves internationalization and diversity in Aalto University and Finland and makes this place even more awesome. €1,000 in Finland is definitely not much (thus a small if not tiny gesture), but i hope this would even a tiny bit help students enjoy Aalto University and Finland, just like I did many years back.
My Acceptance Speech
13년 전 처음 <Probabilistic Robotics>와 <인공지능> 강의를 듣기 전까지 사실 전 machine learning, 자연어 처리, machine translation, 인공지능, 이런 단어들을 들어보지도 못했습니다. 다만 당시 우연찮게 학과 사무실에 앞에 놓여있던 핀란드 헬싱키 공대 machine learning 석사과정 팜플렛을 우연찮게 저와 같이 강의를 듣던 선배가 전달해줬고, 무장적 핀란드로 유학을 떠났습니다.
제가 진학한 석사 프로그램은 당시 신입생들을 신청 없이 무작위로 학과 내 연구실에 배정해서 일주일에 하루씩 연구 경험을 쌓도록 했습니다. 저는 우연찮게 당시 Bayes’ Group이라 불렸던, 이름과 달린 뉴럴넷 연구를 하던 그룹에 속하게 되었습니다. 당시에는 사실 뉴럴넷이 무엇인지도 모르던 시절이었고, 뉴럴넷을 갖고 뭘 할 수 있는지도 전혀 몰랐습니다. 다만 연구실에 일주일에 하루라도 속해서 연구하는 방법을 배우고 다른 연구원들의 연구하는 모습을 어깨 너머로 볼 수 있다는 것만으로도 굉장히 신이 났습니다.
아직 딥러닝이 그리고 인공지능이 지금만큼 뜨지 않았던 시절이라 그런지 이 내용으로 석사를 하고 같은 학과, 같은 그룹에서 박사 과정에 진학한 후에도 대단한 연구를 해봐야겠다, 대단한 논문을 써봐야겠다, 대단한 발명을 해봐야 겠다, 는 생각 없이, 마음 편히 궁금한 것은 공부하고, 새로운 것은 직접 시도해보면서 즐겁게 대학원 생활을 보냈습니다.
이런 대학원 생활 막바지 우연찮게 당시 새롭게 생긴 인공지능 학회인 아이클리어라는 학회에 참석했습니다. 제 기억에 따르면 40-60명 정도만 참여했던 조촐한 학회였습니다. 학회 첫 날 아침 식사에 우연찮게 몬트리올에 있는 Yoshua Bengio 교수 옆에 앉게 되었고 그 아침 식사를 계기로 몬트리올 대학교에 박사 후 연구원으로 가게 되었습니다.
몬트리올에 도착 한 다음날 Yoshua가 앉아있는 제게 와서 4가지 연구 주제를 던져줬습니다. 그 중 하나가 machine translation 이었고, 그에 대해 아는 것 하나 없는 상황에서도 다만 재밌을 것 같다는 생각 하나만 갖고 machine translation 연구를 해보겠다고 했습니다. 그 후 8년이 지났고, 이런 우연찮은 선택들이 모이고 모여 지금 이 자리에서 제게 너무 과분한 상을 받게되었습니다.
본 소감을 준비하다보니 제 공부 및 연구 경력에는 “우연”과 “운”이 많이 작용했다는 생각이 듭니다.
만약 13년 전 용욱이 형이 그 팸플렛을 우연찮게 주어서 갖다주지 않았으면 어땠을까? 만약 12년 전 우연찮게 Bayes group에 배정받지 않았으면 어땠을까? 만약 8년 전 우연찮게 아침 식사를 위해 앉은 자리 옆에 Yoshua Bengio가 없었으면 어땠을까? 만약 8년 전 뜬금없이 machine translation을 선택하지 않고 조금 더 익숙했던 주제를 선택했으면 어땠을까?
이런 질문에 대한 답을 곰곰히 생각하다 보면, 제가 지금껏 이룬 일은 제 개인이 이룬 것이 아니라 생각합니다. 제 성과는 인공지능, machine learning, data science 등 다양한 이름으로 불리우는 분야에 속하는 연구원 모두가 다같이 이뤄낸 수 많은 성과들 중 아주 작은 하나일 뿐이라는 결론에 도다르곤 합니다.
인공지능 연구란 큰 흐름 안에서 좋은 우연의 연속으로 남들보다 살짝 더 드러나는, 하지만 여전히 한 없이 작은 성과를 이뤘을 뿐이라는 것을 생각해보면 제가 개인적으로 이런 과분한 상을 받는다는 사실에 인공지능 연구의 선배, 동료, 후배 과학자 분들께 한없이 죄송할 뿐 입니다.
인공지능 연구의 궁극적 목표는 지능이란 무엇인지, 이성이란 무엇인지 등 감히 과학적으로는 답할 수 없을 것만 같았던 이런 질문에 대한 답을 찾는 것 입니다. 마치 지난 몇 년 또는 몇 십년 간 인공지능 분야에서 대단한 성과가 나온 것 처럼 보일 수도 있습니다만 이런 근원적인 질문에 대한 답을 찾기 위해서는 아직 갈 길이 멀고, 사실 어느 방향으로 전진해야 할지도 막막할 때가 많습니다.
그럼에도 불구하고 호암 재단에서 저희 분야, 인공지능 연구 분야, 에 이런 큰 상을 주셔서 감사드립니다.
지금까지 이룩한 것에 대한 축하보다는, 저를 비롯하여 인공지능 연구에 불철주야 매진하고 있는 교수, 연구원, 개발자 그리고 학생들에게 더 앞으로 나아가라는 격려와 응원의 의미가 담겨 있다고 생각합니다.
인공지능 분야의 모두를 감히 대신해서 호암재단에 다시 한 번 감사 말씀 드리고 싶습니다.
* i know it’s weird to quote myself from another blog post, but i think i said it pretty well when i was asked about how i feel about this Prize earlier.
∘ if you want to know more about the origin and original design of the Macadamia program, see this report.
# i might be off by $N$ here. if any of my peers remembers the correct number, drop me a line so that i can fix it.
@ sadly Finland, as a whole, does not seem to share this goal with me. a few years back (a few years after i left Finland,) Finland introduced tuition for non-EU students enrolled in programs that are mainly taught in English, breaking its amazing tradition of providing free education to all. i seriously believe this was a mistake.
$ the name of the Macadamia program was changed to the “Master’s Programme in Computer, Communication and Information Sciences – Machine Learning, Data Science and Artificial Intelligence”. yes, they changed the name of Macadamia to include “Artificial Intelligence”, which would be the least surprising decision ever..