- over the summer i worked on a military research project in san diego, i’d tell you what i did but then i’d have to kill you
- while i was in san diego, i went to comic-con, which was pretty awesome [i'll post some pics on facebook or something]
- went to las vegas with aziza, where we met william shatner [another thing i need to post more pics of]
- in august i started a computer science masters degree at carnegie mellon (language technologies department specifically).
- haven’t found a research project here yet, but i’m currently writing a research proposal (part of the nsf graduate research fellowship application) for a project involving machine listening and music analysis, and hopefully regardless of whether i find funding through the department i can find some professor here to guide/mentor me on this endeavor.
- saw the police do some questionable things here in pittsburgh during the G20
- bought a sweet fender dreadnought acoustic/electric and have been writing some new stuff, and learning a little slide guitar.  some youtube videos are soon to come
- got cable tv and internet. i hate comcast, but what can you do, they got the market locked in my neighboorhood
- been interesting at carnegie mellon: lots of interesting people come by (Bill Gates), seen some legends of computer science (tom mitchell, the guy who literally wrote the book on machine learning, teaches here), and got some free beer and/or food from different companies (google, facebook, apple, microsoft…)
- got my first paper published, and soon to have two more [hopefullly]
- acted like a jackass and rode down my office building’s 3 story spiral shaped ramp on a roller chair (need to do it again and tape it, cause this gates building is ridiculous)
- and finally, i turned 23 last week… yup

anyways, i’ll post some thing better in the coming  days/weeks…

- kevin d.

http://www.myspace.com/ftfgrunge

Right now we’re calling the project FTF. Basically the band is alternative rock, but I’m aiming for something grungy… we’ll see how it turns out. Anyways check out the songs I put on MySpace; they’re first draft recordings but aren’t too bad… More to come as the other songs I recorded get mixed down and as we write more stuff…

So I told an artist friend about this really weird date I had with a co-worker. The result was the above comic strip. I still wonder about that girl…

One research project that I have worked at the VLM lab involved determining the number of clusters that exist in a data set based on the information provided in nearest neighbor distance matrices. A possible application of this work could be to determine how many unique people appear in a set of pictures where each person would be considered a clustering class. The idea for this project is novel, in that it could determine the appropriate number of clusters regardless of the distance measure.

Our approach hinged on the assumption that the objects described in the distance matricies where, for the most part, distributed uniformly in some hyper-dimensional euclidean space. Then by using some basic geometrical operations, we can determine the intrinsic dimensionality of a dataset and in turn use different bounding parameters to determine if certain objects were just too close, probabilistically speaking, to be in the general uniform distribution of the rest of the space and must therefore belong to the same clustering class.

I approached this problem, under the guidance of my advisor, by first coming up with a theoretical model and then running some experiments on mock data to verify the validity of our assumptions. The initial results were encouraging, but we are currently trying to resolve some unexpected issues we have faced with objects distributed in higher dimensional space.

The first non-trival task of this project, and ultimately the current stumbling block, is figuring out a way to determine the intrinsic dimensionality of a data set. At first I experimented with coming up with models that based on hyper-dimensional spheres, or rather a set of concentric hyper-dimensional spheres that could be viewed as cores, and came up with some intuitive rudimentary relationships. The problem presented by this approach though was that often times our hyper-dimensional sphere would spread beyond the actual limits of our datasets, and would therefor skew the results. My advisor and I quickly realized that such events would also be more relevant as we moved into higher dimensional spaces.

So we thought of different ways to solve for intrinsic dimensionality, the most promising being based on linear projections/embedings. But after a week or so, my advisor decided to focus on another, and arguably more interesting, project. I still feel that a solution could be found to this problem and I would like to revisit it some day, when I have a better background in the field.

My name is Kevin Dela Rosa, and this is my blog. I live in a suburban city in Dallas county called Cedar Hill, and am currently pursuing a Bachelors degree in Software Engineering and Physics at the University of Texas at Arlington.

I’ve recently decided to keep a personal log of the events in my life in order to have a record to look back on sometime in the future. This blog will serve as a vessel for my ideas and host for conversations with the online community. Also, I work as a research assistant in the Vision Learning and Mining (VLM) lab, and will use this blog to document some of the research I perform.

I’m doubtful that anyone really cares about what I have to say, but I’m putting it out there anyways.

-Kevin