atlhack.org aggregator

What is your best paper? Ambigous! [Computational Complexity]

Fri, 21 Nov 2008 13:00:55 -0500

Be a JavaOne Rock Star [Duke Listens!]

Fri, 21 Nov 2008 11:36:21 -0500

The JavaOne call for papers is now open Speaking at JavaOne is fun, but also a lot of work. Here are some images from last year (courtesy of flickr):

A New Scholarship for Making Games [Grand Text Auto]

Fri, 21 Nov 2008 11:17:03 -0500

As reported earlier this fall by the San Jose Mercury News and others, UC Santa Cruz recently received more than $450,000 from Sony Computer Entertainment America (as part of a class-action settlement) to fund undergraduate scholarships. I’m happy to announce that application information is now online. The first scholarships will be available to students applying [...]

Story Generation in 1K [Grand Text Auto]

Thu, 20 Nov 2008 21:54:33 -0500

Michael’s here at MIT and just gave a great talk. While he was preparing for it, apropos of conversations I’ve had recently with him and Beth Cardier, I wrote something that I think is a story generator, and which is a self-contained 1K python program. Here it is: story.py Let me know if you think it’s [...]

Bugmail Extension for Thunderbird [Hacking for Christ]

Thu, 20 Nov 2008 12:15:16 -0500

The lazyweb works! You can now get the experimental Bugmail Extension for Thunderbird. Many thanks to Fabrice Desré. I've just installed it and it does exactly what I want....

Is the Medium the Message? [Computational Complexity]

Thu, 20 Nov 2008 11:00:35 -0500

Reflection on the old days- by Joseph Kruskal [Computational Complexity]

Wed, 19 Nov 2008 13:00:33 -0500

Jonathan Coulton on CC [Lawrence Lessig]

Wed, 19 Nov 2008 11:29:57 -0500

From the CC Blog: The ever innovative Brooklyn-based singer songwriter Jonathan Coulton has teamed up with Creative Commons to release his greatest hits compilation “JoCo Looks Back” on a 1gb custom Creative Commons jump drive to help support our 2008 campaign. If that weren’t enough, JoCo and CC have also included all of the unmixed audio tracks for every song on the drive. That’s over 700mb of JoCo thing-a-week goodness. Since all of JoCo’s music is released under our Attribution-NonCommercial-ShareAlike license, this is an incredible opportunity for the public to remix and reuse his fantastic music. Song files are in 320kbps MP3 and unmixed audio tracks are in 256 VBR MP3.

We’ll be offering the drives exclusively at our $50 dollar donation level (and above) until December 31st. Also included are a CreativeCommons.net account, an OpenID identity, and a 2008 campaign sticker.

Jonathan also wrote a wonderful commoner letter speaking on how he, as a musician, uses Creative Commons to support himself and his career. Read it here.

The letter is just about the most moving CC writing I've seen.

ISEA Go Bragh [Grand Text Auto]

Wed, 19 Nov 2008 10:57:23 -0500

ISEA 2009 will be held from 23 AUGUST - 01 SEPTEMBER 2009 in Belfast, Colraine, Derry, and Dublin, Ireland. Proposals for papers and art projects are due this Friday, Nov. 21, by midnight. The Inter-Society for the Electronic Arts (ISEA) is an international nonprofit organization fostering interdisciplinary academic discourse and exchange among culturally diverse organizations [...]

Two on Turbulence [Grand Text Auto]

Wed, 19 Nov 2008 00:16:14 -0500

New on Turbulence.org: “Bronx Rhymes” by Claudia Bernett and Maria Ioveva. “Bronx Rhymes” illuminates the history and significance of Hip Hop in the Bronx by tagging important locations for Hip Hop (1520 Sedgwick, for example) with posters. Each poster describes the historical significance of that location in the form of a rhyme, and invites people walking [...]

The Old Games and Art Question [Grand Text Auto]

Tue, 18 Nov 2008 23:38:05 -0500

I wanted to call everyone’s attention to an article by Chris Crawford about whether games are art, published this summer in Notes On Game Dev. The article offers many interesting observations, and I suggest that those interested in the question read it. My purpose in mentioning it, however, is not to repeat it, rephrase it, [...]

Secrets from the Future [Computational Complexity]

Tue, 18 Nov 2008 09:00:43 -0500

Going where no collaborative filter can go [Duke Listens!]

Mon, 17 Nov 2008 20:05:38 -0500

Most music recommenders use some form of collaborative filtering to connect listeners with new music. That's not a surprise, CF works really well for popular music (which, of course, is what most people are listening to). But if you are interesting in long tail music, music that is unpopular (or perhaps music that is brand new and doesn't have any listeners), then you are out of luck A collaborative filtering algorithm cannot help you -- CF recommenders rely on the wisdom of the crowds, but that leaves them impotent when there are no crowds. One approach to the problem of dealing with new (or unpopular) content is to use a content-based recommender - instead of making recommendations based upon who is listening to a song, the recommendations are made based on what the song sounds like.

We've seen a few commercial music recommenders that rely on content-based techniques - MusicIP, Echo Nest, Ghanni, One Llama, Audiobaba, Owl, SoundFlavor and Pandora have all had some aspect of content-based recommendation at the core of their systems. Now there's another content-based recommender to add to the list of contenders - mufin.

Mufin (which stands for MusicFinder) is a content-based recommender that (according to Techcrunch) is an offshoot of Fraunhofer (the folks who invented the MP3). Given this pedigree, I had very high expectations for Mufin.

The Technology From the Mufin Technology page:

mufin uses mathematical extraction of specific details from a music title to create an objective desciption of the title?s characteristics which is independent of human influences. Using this description, songs which are similar to one another can be filtered out of a large database. Rhythmical characteristics (e.g. intensity of the rhythm, tempo, percussion in the piece), sound colour, harmonic and melodic qualities are weighted differently for the result.

My Impressions I was lucky enough to get a invitation to the Mufin private beta - so I took it for a spin - here are my impressions.

The Mufin site is very simple to understand. It has a classic search box where you can search for an artist, album or track. Since there are nearly 5,000,000 tracks in the catalog you are bound to find what you are looking for. I searched for bands like Deerhoof, ELP, The Beatles, Hannah Montana, The Feelies, and the Rheostatics. Mufin had them all. Unfortunately, Mufin won't let you play back all of the songs in the catalog - some songs can be played all the way through, some you can play 30 second excerpts, and some are not playable at all - this is, no doubt due to the crazy licensing issues that plague digital music. Mufin also lets you purchase tracks from iTunes - (allowing Mufin to make some money via referrals).

The Recommendations Of course, searching for music is no big deal - what we are interested in are the content-based recommendations. So lets check them out.

Whenever I try out a new content-based recommender, the first track I usually try is Revolution #9 by the Beatles. This is a good way to find out if a recommender is really a CF recommender trying to pose as a content-based recommender. Revolution 9 is so unlike any other Beatles song (or any other Rock or Pop song recorded in the 70s) - that recommendations from a content-based recommender will yield very different results than what you'd get from a CF recommender. Using Mufin to find music similar to Revolution #9 yielded a rather strange grab bag of music: Some Wagner, Engelbert Humperdink, UFO, Gershwin, The Disney Aladin Soundtrack, Frank Sinatra, and Ella Fitzgerald. No 70s pop, which is a good sign, but the results seemed to be strongly under the influence of a random number generator. Not a very good start - but since Revolution #9 is not your typical track perhaps these results were an aberration.

So I moved on to something a bit more conventional - some power pop with from Weezer. I tried the track 'My Name is Jonas'

These results looked better with tracks by Foreigner, Cell Division, Guano Apes, Dream Theater. However, there was also quite a bit of heavy metal - Rhapsody, Kamelot, Dio - that didn't really seem to fit to well.

Next up was some cool jazz - Take Five by Dave Brubeck. For similar tracks I did get some cool jazz like McCoy Tyner, but also some salsa, some crash test dummies, some blues by McCracklin and Louisiana Red (good stuff, but not anywhere near the cool jazz and syncopated rhythms of Brubeck), some female vocalist/country music by Frances Black, Gospel music by the Jackon Southernaires. Again it seemed like the random number generator was working overtime on this set of recommendations.

Next up was Led Zeppelins venerable classic Stairway to Heaven:

The recommendations included soul music by Aaron Neville, minimalist electronica (tubular bells), classical piano (Mussorgsky), easy listening (Englebert Humperdink, Paul Anka). There was no need to 'get the led out' of this list. One has to wonder about a recommender that puts Engelbert Humperdink in the same list as Mussorgsky's Pictures at an Exhibition.

Finally I tried some classical music - with Beethoven's Fifth symphony.

These recommendations seem to be much better - the recommendations include some more Beethoven, there's Hayden, Handel, Tschaikovksy, Mozart, Chopin, Dvorak and a number of classical film scores.

Summmary The Mufin folks have done a good job putting together the Mufin site. They've indexed an incredible amount of music. The search engine and the recommender engine are fast. The site design is clean, and easy to use. However, the content-based recommendations provided by Mufin don't fair well when compared to the type of recommendations one can get from a CF filtering recommender. There is a very high rate of 'clunker' tracks that no human would ever recommend based upon the seed track. For some seed tracks, the recommendations seemed no better than shuffle play -while for others especially classical, the recommendations seemed to be pretty good.

The Mufin team are working hard to improve their recommendations - I hope they get the kinks out - it would be nice to see long tail, content-based recommendation become a reality.

London Pub Trip [Hacking for Christ]

Mon, 17 Nov 2008 16:48:22 -0500

dougt and Lucas Adamski are coming to London, and we're meeting up for a drink on Wednesday 10th December. If there are any Mozilla people in London at that time who'd like to join us, drop me a line....

A "well known" theorem [Computational Complexity]

Mon, 17 Nov 2008 15:01:20 -0500

Visualizing last.fm [Duke Listens!]

Mon, 17 Nov 2008 07:08:51 -0500

PhD student Last.fm Employee Nepusz Tam�s has created some nifty and rather intriguing plots of the last.fm artist similarity space at his site: Reconstructing the structure of the world-wide music scene with last.fm .

Update: There's a super-zoomable version on the seadragon gallery page. I can't figure out how to directly link to the image ... It is the 5th one from the right. The plot is created by crawling the similar artist graph of Last.fm (starting with Nightwish of all places) using the last.fm audioscrobbler webservices. The artists are arranged on the graph using a DrL graph layout algorithm (DrL is a force-directed layout algorithm that works with very large data sets. More info about this algorithm can be found in this paper ). The nodes in the graph are colored based upon the most frequent tags, while the edges are colored based upon their 'betweeness centrality score'. The area of a node in the graph is approximately proportional to the popularity of the artist.

Nepusz has also created an interactive map that allows you to type in the name of a few artists to see where they live on the map - or you can just enter your last.fm user name and it will show you where all your favorite artists are in the world of music.

The layout algorithm does a pretty good job of showing the large scale structure of the artist space. Artists with similar genre tags are well clustered. The ability to see where a particular artist is located on the map is very nice and the last.fm user integration is particularly sweet. Interesting too, is how the popular artists seem to be clustered in the graph. The larger vertices in the red-rock area form a very tight line. This may be an effect of using the Last.fm artist similarity which has a popularity bias (the top 10 artists similar to the beatles are all very popular artists).

What I really wish I could do is to use these plots for music discovery - I'd like to be able to mouse over a vertex to see what the band is (and even be able to listen to the band). It would be really interesting, for instance, to explore the point where the electronic and the rock world meets (like in the subsection of the graph shown here on the left - what artist is represented by the large orange node?). It'd be interested to see what the outliers are (I wonder what this reggae/ska artist is doing near the jazz, as seen in the subgraph on the right). I'd like to be able to zoom in and see some of the finer structure (if I zoom in on the Nightwish neighborhood, do I find more finnish, gothic metal?).

I'm a sucker for such visualizations, I think they can be a powerful tool for helping people to understand and explore a music space, and they can reveal relations and structure that are not evident in simple lists of similar artists. But creating these visualizations are not easy. Without special care they can easily turn into meaningless blobs. Nepusz has done an excellent job finding the right embedding algorithm, color and sizing strategy for the data. I hope he continues to add interactivity to his plots. Well done.

Observations on Linearity for Reductions to Regression [Machine Learning (Theory)]

Sun, 16 Nov 2008 19:54:59 -0500

Dean Foster and Daniel Hsu had a couple observations about reductions to regression that I wanted to share. This will make the most sense for people familiar with error correcting output codes (see the tutorial, page 11). Many people are comfortable using linear regression in a one-against-all style, where you try to predict the probability [...]

Ahora en espa�ol: Venenarius Verborum [Grand Text Auto]

Sun, 16 Nov 2008 17:10:26 -0500

Jarel presenta Venenarius Verborum (video): Tras el misterioso fallecimiento del brujo propietario, el a�o pasado, sus herederos pusieron inmediatamente en venta la torre. No faltan potenciales compradores para la finca, pero existe un grave problema, y es que la torre es indestructible, inquebrantable… o lo ser� mientras persistan en ella ciertos objetos que el brujo encant�: Los [...]

IF Comp 2008 Results: Congrats, Violet! [Grand Text Auto]

Sun, 16 Nov 2008 17:01:02 -0500

Violet, Nightfall, and Everybody Dies are the top three games in the 2008 Interactive Fiction Competition, after a month and a half of play and voting by the public. Congratulations to Jeremy Freese, Eric Eve, Jim Munroe, and the authors of all the entries. You can still download all the games, of course. The full [...]

Bugzilla Runs NASA [Hacking for Christ]

Sat, 15 Nov 2008 16:48:39 -0500

How cool is this? Yes, the post title is the right way round....