Bumblebee

Almost every Friday at 3pm there is a talk at McGill’s Computer Science department. Today was definitely one of the coolest ones: two members of the team that won the Netflix prize gave a talk on their machine learning techniques. Martin Chabbert and Martin Piotte, graduates of the Ecole Polytechnique de Montreal were members of BellKor Pragmatic Chaos that won the $1 million, 20 minutes before the deadline. Among the most interesting lessons in their fascinating talk, was the fact that at the end they had intelligently combined about 800 predictors using machine learning techniques and clever approximations. However, as they said, it was becoming evident towards the end of the competition that the only way to win, by hitting the mark of 10% improvement on Netflix’s movie recommendation algorithm, was to join forces with other teams, namely BellKor and BigChaos  — explains the weird team name. This meant sharing technical expertise, sharing predictors to be combined in ensemble classification, and of course sharing the money Here are the technical documents that explain how they did it: Pragmatic Theory, BigChaos, BellKor.

This week was my first week of classes at McGill and my second in Montreal. Being a grad student is quite enjoyable at the moment: I have more freedom in my course selection than when I was an undergrad, I get to explore the topics I’m studying in a greater depth than before, and generally the whole feeling of starting at McGill as a new student is quite exciting. Living independently in Montreal has its perks: a very vibrant and creative European-like city with a large student population, plenty of interesting activities to engage in and lots of opportunities to learn French. For now, I want to write about something other than Montreal, though, which I am sure is going to come up frequently in future posts.

My coursework for this semester, which I hope I have chosen so that it is neither too easy nor extremely time-demanding looks like this:

• Computer vision. While there is no required textbook, I think I am going to consult a couple of recommended ones, namely Introductory Techniques for 3D Computer Vision and Computer Vision: A Modern Approach

• Computer graphics. There is no required textbook in this course either. The OpenGL Programming Guide is a recommended one, and I suspect it’s going to be quite necessary for our assignments, but I think I should also consult Fundamentals of Computer Graphics and some online articles and tutorials because I feel that the lecture notes leave me with many questions.

• Machine learning. Pattern Recognition and Machine Learning is a classic and so seems to be Reinforcement Learning: An Introduction. This course has about seven assignments and a big final project that will include a report and an in-class presentation.

Needless to say that all of these courses require careful preparation and equal attention. I should also keep in mind that I’ll have to start reading a couple of papers each week to familiarize myself with the work that is being done at the Mobile Robotics Lab. I’m still not sure whether I should spend the rest of the time learning French or experimenting with something I haven’t tried before — I’ll just have to see how the following couple of weeks will be.

A very good friend of mine gave me a detailed list of todo items that I’d better try out in Montreal. I don’t think she’ll be very mad at me for sharing them here:

• Mont Royal.  There’s a cross somewhere up at the top, which can be seen quite clearly when it’s illuminated at night.  Try figuring out how to actually climb up to it.  There’s also a viewing area about halfway up the ‘mountain’ (it’s really just a really tall hill) from which you can see all of downtown Montreal.

• Schwartz’s Deli.  http://www.schwartzsdeli.com Order a smoked meat sandwich (I would suggest either ‘medium’ or ‘lean.’)  Get a pickle with it and enjoy the best smoked meat in the country.  If you don’t like the sandwich, then you can be quite certain that you don’t like smoked meat.

• Gelato in the Old Port.  Right around Place Jacques Cartier (the Eastern most section of the Old Port) there is an entire strip of good gelato/ice cream places.  They’re all just west of the Place JC, on Rue De la Commune (the southernmost street).

• St. Denis, the Plateau, The Village part of St. Catherine Street. There’s a building somewhere downtown that has a piece of the Berlin Wall on display.

• Eat crepes.  If you find some with Creme de Marron (chestnut cream/paste/jam), try it!

Thank you for the orders suggestions Z.C., I’ll happily follow them

graduation hat toss

After four years in the making, I graduated from the University of Toronto, got my Honours B.Sc. in Computer Science & Math and celebrated the finale of my undergraduate life with my family and friends. Looking back at these four years I realized that it was definitely a process of growth, both professional and (especially) personal. What stimulated this growth was the decision I made early on when I started my studies at UofT:  to do well in a demanding academic environment, and at the same time have fun and do exciting activites outside of the classroom. I wanted to explore as much of the world that was unknown to me as possible, without putting school to a second fate.

Along the way I tried things that I hadn’t tried before I went to university: from baseball to salsa dancing, from white water rafting to skating, from juggling to driving a car (I still find a lot of similarities between the two), from camping in serene nature to exploring big cities, from playing the guitar to programming robots.

I also met a lot of interesting people who opened up a sea of possiblities for me. The funny thing is that most of them didn’t realize the positive effect they had on me. Fortunately, I tend to notice details in their stories that are invisible to them.

Academically, I took a range of stimulating courses. I managed to become better in programming, and I even learned a new language: mathematics. It is amazing how many people speak it and how it connects those people. On the flip side, those who don’t speak it or have never tried to learn it tend to look at you as if you just escaped from an asylum — especially in parties I remember once talking to a member of the Glendon Musical Ensemble (a very beautiful bilingual campus, part of York University, where most students study psychology, french, english and arts). After she introduced herself, she asked me what do I study. I swear that my answer horrified her and her eyes passed through a number of phases: first denial (it can’t be…there are actually people who study those things?), then silent contemplation (what kind of a person would study something like that?), then disgust (ewww). OK, fine, maybe I’m exaggerating, but you get the point: math usually makes it difficult to be immediately accepted by people who hate it, because they assume they can infer everything their is to know about your personality just by the fact that you’ve decided to study something they consider hard and hideous. That said, I am always amused by how quickly their impression changes as soon as they make the effort to get to know you a little better; all the stereotypes collapse.

So, thank you UofT for the last four amazing years! Hopefully our roads will cross again in the future. In the meantime, my next journey is going to begin in September at McGill University. I’m going to do my M.Sc. at the School of Computer Science, hopefully working at the Mobile Robotics Lab or the Reasoning and Learning Lab. I’m looking forward to the adventures I am going to have in Montreal.