GRE

I took the GRE this morning. It started with two writing sections. My essays weren't spectacular, but the topics were interesting so at least I had something to write about. The next section was the math section. I did really well on this and finished just barely on time. I switched the answer for my last question with less than 5 seconds to spare! Next was a verbal section which went about as well as could be expected (English is not one of my strong points). I thought that would be the end of the exam but was surprised when another math section started. My practice tests only had one math section so I was annoyed that the test wasn't finished. This second math section went terrible since by then I was getting tired. I was working way too slow and still had 7 questions remaining with only one minute left. I had to randomly guess for the last few questions. I was surprised to see in the end that my scores were 800 in math and 600 in English. I am really lucky that the second math section must not have been scored. Apparently they put in an extra unmarked experimental section. I will have to wait for the scores to be sent to me before I get the marks for the essays.

Internship Finished

I finished my internship at Microsoft last Friday. It has been a great summer. Almost every weekend there was some Microsoft event taking place. I took part in two puzzle events. One of them was non-stop for 36 hours and really well organized (our team came in third)! A few weeks ago I went cave exploring at Ape Cave Lava Tube near Mount St. Helens. Two days ago (my birthday) I saw Dark Knight at IMAX - incredible movie.

On August 30th I will be taking the GRE. I haven't done much studying for it yet, so I plan on studying for the next few days. Over the next semester I will start applying for grad schools. I have decided where I will be applying for six out of my nine applications:

- Carnegie Mellon
- MIT
- Stanford
- UBC
- Waterloo
- University of Toronto
- ?
- ?
- ?

The other three will most likely come from this list. I will be applying to AI programs. I am currently planning to focus on learning about pattern recognition. Since I eventually plan on doing industry research, hopefully I can get research internships over the next few summers.

Comics

Summer

I have been working for Microsoft for almost a month now. So far it has been a great experience. The company has a ton of amazing benefits and it has been really interesting learning about their software development practices. I am working on a product called Office Live Workspace. There have been a lot of fun intern events such as a poker night, video games, movies, and a trip to the zoo. I have also attended a few research/tech talks on campus. We get all the free drinks we want here and also occasional free food (if you know where to look).

There are a lot of things to see and do around Seattle. A few weeks ago I went to the Pacific Science Center. I think its better than the one in Vancouver. I saw Speed Racer at IMAX. It was pretty dissapointing, but I wasn't too surprised based on its score at IMDB. Yesterday I went to see a Cirque Du Soleil show called Corteo. It was an excellent production, but I liked the Mystère show I saw in Las Vegas better.


I got a new bike earlier this month. There are supposed to be some really nice bike trails in this area, so I plan on exploring a few of them over the summer.

Here is a photo album I will be uploading pictures to over the summer.

Netflix Prize

One of my summer projects will be working on the Netflix prize. It is a competition to write a program to predict user ratings of movies. We are provided with a huge dataset of actual user ratings from the Netflix database. We are also provided with a test set of <user, movie> tuples for which we need to predict ratings. After submitting the predictions Netflix returns the root mean squared error (RMSE) for a subset of the test set. Netflix already has the actual ratings for the test set, which is how they score the predictions. The three submissions I have made so far have gotten the following RMSE:

1.0533
0.9992
0.9844

Netflix's own algorithm (Cinematch) gets a RMSE of 0.9525. In order to win the competition and get the one million dollar prize a team must have a submission with a RMSE below 0.8572. The best team currently has a score of 0.8643. The three submissions I have made so far just use basic statistics for the predictions. I have three main ideas on how to approach the problem - two of them involve clustering algorithms and one of them uses temporal neural networks.

Temporal Patterns

I have finished implementing a neural network framework for detecting temporal patterns. I made a small demo of it using a single bit input. In theory the framework should scale well to much larger problems with many inputs. It is capable of detecting both spatial and temporal patterns and making predictions of what the next input will be. The framework can be used for a huge variety of applications and problems. I tried testing it for part-of-speech tagging but the results were disappointing. Due to the huge number of neurons/inputs I had to use, the network was taking several seconds to process each input. Since the network needs to be trained on huge corpora consisting of thousands of words, it would take a really long time before it can make accurate predictions. A good property of neural networks is that they are highly parrellelizable so that all of the neurons can be processing information at the same time. On a single CPU my computer processes information for one neuron at a time. Given the right hardware, neural networks can have a constant upper bound on computational time. This means that an arbitrary number of neurons/inputs could be added to the network without affecting the processing time.

First Publication!

A paper I have been working on about AIspace has been accepted for publication at the AAAI 2008 AI Education Colloquium. I will be headed to Chicago on July 13th!

Knoll, B., Kisyński, J., Carenini, G., Conati, C., Mackworth, A., Poole, D. 2008. AIspace: Interactive Tools for Learning Artificial Intelligence. In Proceedings of the AAAI 2008 AI Education Workshop. BibTeX

RoboCup Simulator

Here is a short video of what the simulator I made for the RoboCup soccer competition looks like:

[link]

The low quality video is due to the fact that I recorded my monitor using a digital camera. I tried a variety of screencast software (ffmpeg, vlc, xvidcap, istanbul, and vnc2swf) but none of them could capture at decent quality/framerate. I think its time to upgrade my computer (this one is now four years old).

In the video the red team has been assigned the "offensive" strategy and the blue team has been assigned the "dibs" strategy. I haven't implemented all of the RoboCup rules yet (e.g. the ball always gets reset to the center when it goes out of bounds). You can learn more about the AI by reading a report I wrote for one of my classes.

Code Quality

Meet Jon Arbuckle

Apparently an unfunny comic strip can be made hilarious with some minor modifications. Above we see Garfield minus Garfield. The comic strips below are referred to as Realfield. Making a strip out of random Garfield panels can also lead to some amusing results.

Patterns

The universe is chaotic. Within the chaos there are patterns. These patterns are due to emergent properties of relatively simple rules underlying the unimaginably complex interactions of matter. Patterns can be found almost anywhere in nature, from the organization of stars and galaxies to the symmetry of ice crystals in a snowflake. This phenomenon is not unique to nature; incredibly complex patterns can be observed by applying very simple rules such as in the Mandelbrot set or in cellular automata. These emergent properties are also responsible for the origin of life on Earth and the evolution which guides it.

M74 Spiral Galaxy

Life is a striking example of the organization of matter. When suitable chemical and physical conditions arose in early Earth, organic compounds eventually organized themselves into a form allowing self-replication. Natural selection takes advantage of patterns in an organism's environment to gradually optimize its suitability for a particular environment. This process has lead to the huge variety and complexity of life forms seen today. The process of evolution has also created patterns within its creations, such as the fractals seen in Romanesco broccoli. Intelligent biological systems have evolved to actively recognize and exploit the patterns in their environment in order to gain an evolutionary advantage. Learning from the success of biological cognition may help in the pursuit of creating truly intelligent machines.

Aloe Polyphylla

A crucial step in designing an intelligent machine is understanding the fundamental ways in which patterns are organized in nature. The ability to accurately predict and complete patterns allows a system to act intelligently in its environment. In order to make predictions about patterns a machine needs to be capable of learning from past experiences and recognizing both spatial and temporal patterns. Almost all current neural network techniques are only capable of detecting spatial patterns and cannot detect patterns through time. The fact that the human brain is capable of intelligence provides proof that intelligence is possible given limited computational resources, giving hope that computational intelligence may be achieved in the near future.

Terror

This morning I woke up in an extremely unpleasant way. While I was still blissfully asleep I heard some scratching sounds coming from somewhere close to my head. I groggily opened my eyes to see a squirrel staring down at me from the windowsill directly above my bed. In horror I made some loud noises and quick movements with my arms in the squirrel's direction. This successfully got the squirrel to flee out of the window.

Reading Week

Reading week has been amazing so far. Today I went on a bike ride to Stanley Park. I went around the seawall and then rode back to UBC. I was having so much fun that I decided to do some biking around Pacific Spirit Regional Park as well. I regret not bringing my camera since there was some beautiful scenery. I have also been watching lots of anime, reading, working on some programming projects, and playing tons of video games. I accepted an internship position from Microsoft, so I am really looking forward to working there over the summer.


Unfortunately our team didn't make the qualifiers for the RoboCup competition in China. We are going to be working on trying to qualify for a regional competition instead. The AI is progressing well. I made a simulator so we can continue working on the AI without needing physical robots. We have finished most of the lower level behaviors so I am going to start making some different playing strategies. Different strategies can be assigned to competing teams, so simulating matches will show which strategies are superior.

Video Games

After a pretty bad week (which included four midterms) I am looking forward to reading week. Originally I was planning on going on a road trip to the Rockies with some friends but unfortunately I don't think those plans are going to work out. With the free time I will finally get a chance to enjoy some video games I have been waiting to play:

-The Longest Journey (PC)
-Grim Fandango (PC)
-BioShock (PC)
-Final Fantasy XII (PS2)

I just finished installing Windows XP to replace my Vista partition. After struggling to get The Longest Journey working in Vista, I eventually gave up and decided to reformat the partition. It just doesn't make sense for me to be using Vista when the only reason I have a Windows partition in the first place is to take advantage of its compatibility.

Here is a list I compiled of some of my favorite games:

Adventure:
-Legend of Zelda: Ocarina of Time (N64) and Legend of Zelda: Majora's Mask (N64)
-Beneath a Steel Sky (PC)
-Day of the Tentacle (PC), Full Throttle (PC), and The Dig (PC)
-Monkey Island series (PC)
-Myst series (PC)

RPG:
-Baldur's Gate II: Shadows of Amn (PC)
-Star Wars: Knights of the Old Republic (PC)
-Final Fantasy VI (SNES), VII (PSX), VIII (PSX), IX (PSX), and X (PS2).
-Elder Scrolls IV: Oblivion (PC)
-Chrono Trigger (SNES) and Chrono Cross (PSX)
-Guild Wars (PC)

FPS:
-The Orange Box (PC)
-Quake (PC) and Quake III Arena (PC)
-Crysis (PC)
-Deus Ex (PC)
-Unreal Tournament series (PC)

Action:
-God of War (PS2) and God of War II (PS2)
-Prince of Persia: The Sands of Time (PS2)
-Shadow of the Colossus (PS2)
-Super Mario 64 (N64)
-Another World (PC)

Strategy:
-Advance Wars (GBA)
-Total Annihilation (PC)
-Rise of Nations (PC)
-Sacrifice (PC)
-Black & White (PC)

And for the sake of completeness, here is a list of all the consoles my family has owned:
-Atari 2600 (1977)
-Nintendo Entertainment System (1983)
-Sega Mega Drive (1988)
-Game Boy (1989)
-Game Gear (1990)
-Sega Mega-CD (1991)
-Virtual Boy (1995)
-Nintendo 64 (1996)
-PlayStation 2 (2000)
-Game Boy Advanced (2001)
-PlayStation Portable (2004)

一週間

Last Sunday I went out with some friends to see a new ferry that BC Ferries is introducing into the fleet. We got a complete tour of the ferry (including the engine room and the bridge). We also got a free cookie, a drink, and a balloon! One of my friends was interviewed and appeared on the local news.

I had two job interviews last week. The first one was a phone interview with IBM on Monday. I am applying for the Extreme Blue program. The second was an on-campus interview with Google on Friday. I think the Google interview went better than the IBM one. I really don't like phone interviews. They actually made me write code and dictate it over the phone. As I was reading it aloud I noticed mistakes in my code and started trying to correct things. I even started doing crazy stuff like changing variable names and adding features to the code as I was dictating. Of course, this turned out to be a terrible idea since I immediately lost track of what I was trying to do and got confused -_-. I have another phone interview with them in a week, so this time I will try to act a little less flustered.

On Thursday Google invited all the interviewees to a dinner. I thought this was a great event - a good opportunity to learn more about Google, eat free food, and get a Google umbrella. The problems in the Google interview were similar to a typical programming competition. There were three problems which I had to solve and provide time and space complexity. After solving the initial problem, two of the problems had additional twists to make them a bit more interesting.

Today I attended a talk by David Suzuki. I really enjoyed the talk. He is an excellent speaker and covered a wide variety of topics. He started with some background information about his early life and academic career. The main focus of his talk was the potentially negative impact academic research can have on society. He also discussed topics such as Canadian politics, racism, genetics, and ecology. I found it amusing that he voiced a few direct criticisms about UBC. One of these criticisms was the fact that the high tuition fees for international students is not justified and discourages diversity. Another criticism was that UBC Forestry has biased views about logging in British Columbia due to the fact that logging companies are sponsoring and providing financial support to the faculty. After the Suzuki talk I went directly to a presentation by Business Objects. I don't think this is the type of company I would like to work at (I will not be applying for an internship there this summer) but at least there was free pizza.

AIspace Release

We have redesigned the CIspace website and changed its name to AIspace. The new website URL is http://aispace.org. The old CIspace website will continue to exist until March 1st, after which all CIspace URLs will be automatically forwarded to AIspace. Here are some of the technologies I used to redesign the site:

- Server Side Includes: using SHTML, common sections of the website were placed into a single file instead of duplicating the code for each webpage. This allows site wide changes (such as adding a new tab) by editing just one file instead of having to edit each page on the website.

- Cascading Style Sheets: used to define colors, fonts, and the overall layout of the website.

- HTML validation: all of the webpages have been validated to ensure cross-browser compatibility. A button has been added to the bottom-right of each webpage to check its validation using the W3C validation service.

- The website and applet logos were redesigned using vector graphics in Inkscape.

Mr. Bond

Game Theory in Las Vegas

I tried to use a bit of game theory to increase my odds when gambling in Vegas. Of course, I already know that the casinos have a house advantage so I wasn't surprised to see negative expected utilities when calculating the odds of a game. The rational choice would of course be not to gamble. Instead I just gambled a little.

After doing a bit of research on Wikipedia, some of the games with the worst odds are Keno and slot machines. However, these are the games I ended up playing. The games with better odds such as blackjack and roulettes had much higher minimum bets (especially compared to the one cent slots). Games which involve skill allow you minimize the house advantage.

Keno was slightly more interesting than slots because each casino had different paytables and specialty bets. You can choose bets with different payoffs and different probabilities of winning. I could calculate when one type of bet had a lower expected utility than another.

My brother came into Vegas with his own gambling strategy. Given a game with fifty-fifty odds and double payoff, his strategy was to continue doubling his bet until he wins. In the end, if he had an infinite amount of money to bet, this guarantees that he will win exactly the value of the first bet. For example: lose $1, lose $2, lose $4, win $8, profit=$1. However, with a finite amount of money to bet I tried to persuade him that the strategy does not make any sense. It is risking losing lots of money (with a low probability) and gaining a little (with a high probability). In the end this does not change your expected utility (which is zero for the game I described above). The strategy also doesn't make sense because of the concept of sunk cost. Once he loses money in previous games, it should not affect his future betting strategy. Despite my complaints he ended up making a profit o_o

Kevin Leyton-Brown gave an interesting guest lecture about game theory in my Cognitive Systems 300 class last year. Near the end of class we had several different types of auctions for $5 bills. He let us know that any profits would go to charity. I thought one of the auctions was particularly interesting in which the highest bidder would win the prize as normal but the second highest bidder would also have to pay their bid. This means as soon as there was more than two bids over $2.50 Kevin was guaranteed to make a profit on the $5 bill. I made bids over $2.50 even though I knew it wasn't an optimal strategy (it was for charity after all). Being the second highest bidder you are really tempted to outbid the highest in an attempt to win the prize and avoid a complete loss. Another guy in the class and I continued bidding against eachother until the bids actually got over $5. This means Kevin is getting over $10 for his $5 bill :). I eventually gave up and ended up being the second highest bidder. The highest bidder only lost a few cents while I lost over $5. I thought the auction was fascinating due to the temptation for the two highest bidders to continue outbidding eachother despite going over the actual value of the prize (let alone the optimal maximum of $2.50). I'll keep this auction in mind as a fun thing to try with my friends (except this time I will be the auctioneer).

Vegas

Pictures of my trip can be found here.

December 20:

I left from Vancouver to Las Vegas at 2pm. There was some severe turbulence on the descent into Vegas (enough to start some of the passengers screaming). In Vegas I met my brother, his wife, and her parents. There was a sandstorm when we were driving through town that night so that probably had something to do with the turbulence. The sandstorm was actually interesting to see since I have never been in one before. We were staying at a hotel called Harrah's which was right on The Strip. That night we went to Fremont Street. The massive display on the ceiling was very impressive. The slot machines I used on Fremont Street also turned out to be the only profitable gambling I did in Vegas.

December 21:

We started the day by going to the top of the Stratosphere. This is high enough that you can immediately feel a change in air pressure as you are riding up the elevator. It is way taller than any of the other buildings in Vegas so there are some amazing views. Our next destination was Hoover Dam. On the way there there was some authentic desert with cacti. The dam was a very impressive display of engineering. That night we had dinner at Sam's Town and saw a laser light show.

December 22:

I spent the morning sleeping in while everyone else went to the grand canyon. I had decided not to get tickets to go since it was very pricey. That afternoon we visited a few of the hotels and casinos along The Strip. Each hotel has very unique themes and shows in order to attract visitors. Two shows that I enjoyed were the fountains at the Bellagio and the volcano at the Mirage.

December 23:

We saw a car show in the morning and spent the rest of the day touring The Strip. That night we went to the best part of the trip for me - Cirque du Soliel. We went to Mystère at Treasure Island. This was by far the best circus I have ever seen. The music, theater, and performances combined perfectly to create a magical show. I was so impressed by the quality of it that I now want to see the other Cirque du Soliel shows in hope that they are as good.

December 24:

We went to a few more famous hotels and casinos along The Strip. My favorite building was the Luxor; an Egyption themed hotel/casino in the shape of a pyramid. The MGM had some lions on display. Some other cool places we saw were Caesar's Palace, Paris, New York, The Venetian, and Excalibur.

December 25:

We had a relaxing Christmas, mostly enjoying The Strip and playing some poker. Our hotel had an excellent buffet selection. It was almost overwhelming the number of different food options there were so I inevitably ended up eating way too much. I am fairly sure that I have gained a decent amount of weight in the last six days ;)

December 26:

I had to wake up at 4am to catch a very early flight. I was pleased to see that there was some snow when I returned to Vancouver. Waiting for me at my apartment was the PS2 lens I ordered. I spent about five hours working on the PS2. Although the lens was non-functional when I first installed it, I eventually got it to read original DVDs. It refuses to read any CDs or burnt DVDs however. At least it wasn't a total waste since I can now play a few games in my collection. The fact that it still isn't completely working implies that the lens was not the only problem.

For the rest of vacation I will be splitting my time between Robocup and CIspace. I am also playing the following games right now: Final Fantasy Tactics (on PSP), Grim Fandango, Unreal Tournament 3, and Crysis. Although these are all great games, the game I really want to play is Final Fantasy XII. That is why I have been putting so much effort into getting the PS2 working.

Eyes

I found a cool webpage with a collection of detailed images of eyes. Its amazing how complex the patterns are and the amount of variation there is between different people.


I tried photographing my own eye but it turned out to be surprisingly difficult. Not only are reflections hard to avoid but my eye was half closed in most of the pictures:


I eventually got a picture with a full image of my iris and did some photoshoping to get this:


Not quite as interesting as the other eyes on the webpage :(