cat /proc/claus

Late June, I wrote into my calendar “Thesis countdown - 6 months”. Today I stopped to consolitade my tasks, and just realized that I’m down to two and a half months until my first thesis deadline (the pre-thesis comitee - don’t really have a good name for this in english). Of course, I’m nowhere near 50% done.

So things are picking up in the work/research front. Among my current tasks, I’m writing experiments for two different papers, one with two researchers (one from the U.S. and one from Brazil) who I met at GECCO, and the other suggested by a Japanese professor which visited the lab two weeks ago on a local conference. Also, I’m organizing the arrival of a new Post Doc student in november - making sure he has a desk to study, a roof to sleep under, etc. Finally, I’m writing two papers, one which is the translation of a paper recently published by my laboratory - not sure how that will turn out yet - the other one a paper for a local conference in Okinawa in December.

Between all this stuff, my lab days have been quite busy - but that is not to say that I haven’t enjoyed my free time, though. Mainly I have been doing Geocaching in my weekends - a hobby which consists of talking long walks to find small treasures hiding in interesting/difficult places, with the help of a GPS. I also have an RPG campaign going on, which keeps my creative juices flowing. Next on the schedule is a part-time job playing with some kids on a costume at an English School during Halloween, and a gaming party the next week or so.

I’m also halfway through “Salt: A World History”, a genial book from Mark Kurlansky, where he describes the role salt has played in many different societies over the centuries. Sometimes I can’t but feel that he is exaggerating on the importance of salt for
armies, governments and revolutions. I’ll try to write more about the book once I’m done with it (maybe next week or so).

So things are going mostly well - thesis is coming by and the pace is picking up fast. My only options are to ride the wave or get drowned in worries, so …

When I started my research work in the University of Tokyo, my first topic was the study of Ant Colony Clustering algorithms (ACC). I tried to use some Meta-GA to improve ACC, which was believed at the time to be very sensitive on a number of parameters. It was a fun and exciting research, and I read a slew of very interesting papers. However, eventually I hit a wall on that research, in which the clustering generated by ACC would be too fragmented (one class was broken into many subclasses). I couldn’t solve that problem, so I eventually gave up on this line of research and switched to portfolio optimization instead.

Today, a fellow swarm researcher, Vitorino Ramos sent a link via twitter on a new paper about ACC. The paper was a modeling from ACC to SOM that addressed exactly the “too many clusters” problem I was having. Their key idea was that the ACC could be maping as a sample method for neighborhood clustering. So they kinda got rid of the ants, but solved the problem. It was a bit sad to see someone else solve that problem I couldn’t solve a few years ago, but it was also nice that they cited my ACC paper (even including a figure from it), when describing the problem with traditional ACC.

Got a bit Nostalgic with this…

This weekend, I prepared a survey paper for a Japanese Symposium (which, incidentally, will become the basis of the bibliography chapter of my thesis :-P). I decided that it would be a great opportunity to leave the stone age and start using some bibliography management software. Following suggestions from friends, I tried out Mendeley, Zotero and Jabref - these are my impressions:

Mendeley is developed by some people from last.fm and skype. It has many very sexy features, including the ability to drag a PDF into it, which will create a new entry and pre-fill it with information gathered from the PDF. Mendeley can also update an entry’s fields by searching for its title on the web (google scholar), and the accuracy for this one is very good. The interface was clean and very intuitive - I could easily find all functions that I needed to without having to think/click too much about it, specially the addition of tags/comments to and article.

But (unfortunately, there is always a big But), Mendeley had some pretty big problems. The first one is that it would crash too often - After adding just a dozen or so entries, I would find the desktop application crashing without notice - and worse yet, without error messages or memory dumps that would help me track the problem down. In one of these crashes I lost my entire database (fortunately I was just trying the program at the time, no real data was lost). A secondary problem was that the search function was a bit buggy - If I added a keyword, say, finance, to 6 papers, searching for this keyword would only return 3 or 4 of them.

I hope that they fix those bugs eventually, but until they do, Mendeley is unusable for me

Zotero is a firefox add-on that also claims to be able to search for paper details on the net. This is already one letdown (at least for me) - I want a standalone program, not something riding on a Firefox instance (specially because Firefox is SUCH a memory hog!). Zotero won’t even reside inside a tab, it must occupy the root screen of FF. Also, because it is an add-on, its data (including stored pdfs) is saved in a bizarre location inside the hidden mozilla folder - it would be cool if this was configurable, since it would make things easier to back up. These aside, it had many of the same features that I liked in Mendeley, like searching for paper information on the web, and getting info from PDF’s - although they were a bit clunkier to use - for instance, if Zotero couldn’t find the info from a PDF you dragged into it, you couldn’t just enter the info yourself in the entry, you had to create a new one, and drag the pdf into it. They also had a cool feature to link entries as “related” between themselves.

However, all of the above is pointless when Zotero simply chocked on my bibfile. Not sure if it was FF or Zotero’s fault, but trying to import my references file into Zotero would result in FF locking. Next.

Jabref is a java based bib management software. After installation, it read my bibliography file immediately, without glitches. The program was stable, with powerful options to select/search/group papers. However, the interface was very obscure - it took me a while to find the button I had to click to edit an entry (couldn’t just double click it), and there is no option to add tags (I can add keywords to a field and text-search it, but it is just not as easily automateable). Jabref can only search on IEEExplore, and can’t read PDF metadata (it can, interestingly enough, WRITE pdf metadata though - I wonder what is the point of it).

Anyway, after playing with it for about one hour or so, I got the hang of where most of the functions are. It could really use a “search the net for details of this paper” function that searched more than IEEExplore, or a “read PDF metadata function” for convenience of use, but other than that, jabref is functional enough to last me until the other options get their act together.

In the last day of GECCO, there was little in terms of the conference itself. First we had the GECCO business meeting. A number of CFP were announced, including the CFP for GECCO 2010, in Portland, Oregon. It was also said that there was a plan to alternate GECCO between north america and Europe from them on - I hope it works, I think it would be nice. After that, the winners of the different competitions and awards were announced - no big surprises.

After the business meeting we had a plenary talk from professor J. Holland, who talked about the development of evolutionary computation in the past and present, tying it with the idea of complex systems. It reminded me how nice it is to be in a field where you can still hear talks from its pioneers.

After Prof. Holland’s talk, I attended to one of the Late Breaking Papers sessions, to see the work of Nunes that I mentioned in the previous post. It was interesting, and seemed to fit well with the work that other people in my lab are doing for finance.

GECCO was over, and then I went for lunch with many of the people I were hanging with in the conference. Supposedly, there was a “Conference Lunch”, in a restaurant in Chinatown, but when we got there we could see no one from GECCO - just shrimps. Shrimps. That chinese restaurant, for some reason, had 90% of its dishes composed of shrimps - fried shrimp, boiled shrimp, raw shrimp, yakisoba with shrimp, shrimp pie… some people in our group were getting quite sick of it, but I was loving!

After the lunch, Verena, who was with us, said she was going Geocaching - and having heard about it before, I invited myself to accompany her, out of curiosity. I must say it was one of the coolest things I have done in a while. The idea of Geocaching is that people hide small caches in out of the way locations, or in the city, and then publish GPS coordinates for those caches. You get those coordinates and try to find them. When you do, you can sign a log book, and see what other people have left in the same cache.

Sounds simple enough, but for me the most amazing part of the experience was that 1- it took you to places you would never otherwise see in a town - It seems to me a great thing to do when you are in a place you have never been before (like the conference) 2- it also makes you see places you see every day in a very different way - something is hidden somewhere you pass by every day. Verena was quite a pro at it already, and in about 8 hour walking, we found almost a dozen caches in Mount Royal and the old town. We walked a total of almost 15 km! Quite an excercise too!

And that ended my short trip to Montreal It was a good chance to make contacts with new people, re-establish old ones, see new research, and even do quite a bit of tourism.

The 5th day of GECCO (friday, 10th) was the first day of paper presentations. With only two days of paper presentations (as compared with the three days of GECCO 2008), it felt hard to attend to all the presentations I wanted to. I’ll probably send an e-mail to the GECCO organizing comittee suggesting that they spread the presentations a bit more next year.

Also, since I had to present two works in different sessions, my choices were further limited. Oh well. Anyway, the first session
I attended was “Financial Applications 1″, with two works by Chris Clack, Wei Yan and Ghada Hassan from UCL, which were extensions of their works in the previous edition of GECCO. I particularly like Ghada’s work, which focuses on not allowing a pareto front of solutions to “switch places” (move to a different area of the pareto front) when the environment changes. There was also a work on using developmental solutions for stock trading, which I still have to read more closely (TODO: and refer it to my trading colleagues in the lab).

The second session was the RWA best paper, where I had to present the work on generating trading rules with GP by my labmate Hirabayashi. Unfortunately, as Murphy would have it, my laptop and the projector decided that they don’t really like each other, and would cut communication between each other every few minutes (even though I checked everything and it was alright just one hour before :-(). Oh well. After the presentation, I made the acquittance of Stefan Haflidason, a very pleasant fellow from the UK. We had lunch together and talked about his plans to do a Post Doc in Japan.

In the afternoon, I wanted at first to go to the “GECCO Job Shop”, where poor grad students looking for work would supposedly meet with people with open positions… but no one was in the room. Instead, I had the pleasure to attend to the HUMIES award presentation. The HUMIES is a competition of research works on evolutionary computation which are not only effective, but competitive with human habilities in fields which are traditionally dominated by humans. There is a cash prize to the best work, and all the presentations were of very high quality. Among the candidates, the ones I found most interesting was a system that could find and correct bugs in programs - which was demonstrated on outstanding bugs in varied open source projects! Obviously that one won the prize this year. Other works that I liked were a system that generated malware programs, and a system that used IEC to generate drum accompainment to musical pieces. On a more light hearted note, one of the presenters sounded just like Dr. Strangelove - so much that I was half-expecting his hand to grab his throat at any time during the presentation.

The last session I attended to was second financial applications session, where I presented my own work on Memetic Algorithms for Portfolio Optimization. This time, the laptop and the projector respected each other, and the presentation ran without a glitch. I had a number of questions, and it was a very fine experience.

After the day was done, I tried to get together a largish group of people to go and walk around Mt. Royal - but ran into a complicated constraint satisfaction problem. A group of Romanians wanted to go walking, a group of Japanese wanted to go by train, and everyone had different ideas about how hungry we were. In the end, we separated our 15 people group in two: one to go walking, and one to go by train, and decided to meet by the entrance of the park. By a freak accident of destiny the walking group got to the meeting point before the group that would go by train, which led me to believe that we missed the meeting point. Me and Stefan tried to find the train group, and in doing so, we missed them completely (they got to the meeting point 5 minutes after us) - when we returned, the Romanians had returned home, some people already had dinner, and nobody wanted to go to Mt. Royal anymore :-P. Me, Stefan and about 10 Japanese went to a nearby American-style diner, and managed to salvage the night with some nice lasagnas. After so much walking, I returned home and slept like a stone.

The next day, Saturday, was a bit overcast. The first session I attended was on “Dynamic Environments and Aging” - and it had two papers which were quite relevant to my work. One was the use of ALPS (age-layered population structure) to maintain diversity in the population for Real-Valued problems (by Gregory Hornby). The basic idea of ALPS is to give each individual in a GA an “age” (based on the evolutionary operators it went through), and separate the population into age layers, so that only individuals in the same layer could mate to each other. One interesting point in this particular work is that older individuals tended to be more complex and solve the problem better, and it was suggested during the discussion stage that individuals in different age layers could be trained in different, and progressively difficult, problems, to achieve some sort of developmental property. I found this idea really cool. The second paper which I found relevant was about “Terrain-Based Memetic Algorithms” (TBMA) by Carlos Azevedo and Scott Gordon (couldn’t find any links handy, sorry). The basic idea was to generate a grid, and distribute the individuals of the population in the grid - individuals could only mate with other geographically near individuals. Then for each position in the grid, you assign different parameters for the local search of the evolutionary algorithm. In this way, the movements of the individuals over the grid as they mate and are selected by the fitness function will lead to a self-adaptation of the best LS parameters (the grid locations with the best parameters will attract individuals). I found that this idea can be expanded in a very neat way to my project (and I still have to contact the authors to talk about this.)

After the DEA session, I attended to the game session where I saw Omid’s wonderful presentation about his computer chess player. He has this very simple and elegant idea to train chess positions evaluators using a database of movements from a human grandmaster. In a way, he is reverse engineering the mind of Kasparov. The impressive thing about his current work is that training multiple times on the same dataset, he got a number of chess players with different characteristics. Since he reported that none of his chess players managed to get more than 40% of the answers right, I’m guessing that the difference comes from learning different parts of the database that correspond to different styles of play from the same player. So I guess it is not even possible to go much above this threshold, since the “evaluation” function used by the grandmaster may have been actually quite different for different groups of moves. It is a fascinating work and I can only guess at what Omid will come up with next year.

For lunch, I went back to lovely Rue St. Denis, and to the “Valet du Cour” game shop, to buy a deck of cards that Leon had asked me. I also bough myself a plush green dragon - I couldn’t resist the little beast. It started raining, and I took shelter at local Cafe. All the waiters could speak mostly French with some pidgin english, and I felt a bit ashamed for not being able to communicate properly with them. Need to learn more languages - or at least make an effort to learn the basics out of a phrasebook before visiting other countries.

Because of the rain, I didn’t make it back in time for the third session in that afternoon. I arrived a few minutes before the end of the session, and while I was browsing the net in the lobby, it was curious to observe the network getting considerably slower when the session ended and the influx of geeks turning on their laptops began.

After that we had the plenary session, with a talk by professor Demetri Terzopolous - It did not have anything to do with evolutionary algorithms, but I guess that is kinda the point of a plenary session, right? Demetri talked about is works on the simulation of individuals and societies, describing the framework for realistic simulation of complex creatures, from the physics level to the structural, muscular, reactive and behavioral levels. Plenty of pretty pictures and animations too (Although it got a bit awkward when he showed that strip scene from Animatrix).

At night, we had the main reception at the Montreal Science Center. It was supposed to be GECCO’s 10th birthday, so we had a cake and fireworks (not provided by SIGEVO *g*). It was a good chance to shake hands and talk to many people I had not yet had the chance to meet. In particular, I was introduced to Nuno Horta and his student Antonio Gorgulho, who used my master thesis in some of their earlier works - It may be kinda silly, but it felt nice to know of someone who studied your works!

After the party, I went with Mark and Jeff and a few others for some extra drinks in a bar in old town. It rained quite heavily while we were looking, and none of us had umbrellas, so when we finally picked a place, we were quite drenched. I didn’t stay for long, for I was quite tired, but I heard they had a terrific time there.

And that’s for 5 and 6. Sorry for the delay! I’ll try to get the last part of my travel log online soon, so we can get on with our regular schedule! (I have postponed some stuff I wanted to talk about until I could get these GECCO posts finished).