Comments of ikarpov (11)

Comment on post marriage: the gayening:

Yeah, +1 for the subject.

Comment on post I'm living in my own private Idaho:

where do you play?

Comment on post house-hunting: part 2 of 5000:

You should totally buy Kurt's house.

Comment on post epic flying mount!!:

It is evidence that the blog search index and main index are somewhat disjoint:

Comment on post obsession #12358: bsg:

Also, parsing is going to be noisy for natural language - that's life. If you want something more reliable but not as deep, just do chunking.

Comment on post obsession #12358: bsg:

I'm not sure if it has what you are looking for, but I really enjoyed using NLTK-Lite for NLP stuff. It has taggers, chunkers, parsers, the Brown and the Penn corpora, and other nice stuff.

Comment on post A humbling experience:

Keep in mind that computers and people play the game very differently, so you might also through in a couple live opponents in occasionally.

Comment on post perhaps perhaps perhaps:

I trust you have seen this

Comment on post perhaps perhaps perhaps:

When I hear the phrase "Company X is Chip Manufacturer Y powered", I think of water boilers and steam turbines seating on top of a nice array of overheating pentiums.

Comment on post busy week, fun weekend:

Ooops that link is actually

Comment on post busy week, fun weekend:

Classifying, indexing and clustering music has been an interest of mine for some time now. I tried a hidden markov model, self-organizing maps, and a few more esoteric NN architectures. In general, what you are looking for is papers on "query by humming". I would be curious to see if you can get an efficient implementation of it using one of the streaming database systems, perhaps using dynamic time warping distance-based indecies. We dug up some references for this during a class presentation last semester for a database implementation course. Eamonn Keogh is a good guy to look at for time series clustering and indexing research.

This backup was done by LJBackup.