cameron.freenode.net changed the topic of #mlpack to: http://www.mlpack.org/ -- We don't respond instantly... but we will respond. Give it a few minutes. Or hours. -- Channel logs: http://www.mlpack.org/irc/
< naywhayare>
I would suggest downloading mlpack, compiling from source, then going through some of the tutorials to perform some simple machine learning tasks like nearest neighbor search, k-means clustering, naive bayes classifier, etc.
< naywhayare>
that should give you a good handle of how to work with mlpack
< naywhayare>
then you can take a look through the list of bugs on mlpack.org/trac/, and maybe you can find one that interests you, or maybe you can implement an entirely new machine learning algorithm for mlpack
< tarun_ml_enthusi>
thank you :)
< naywhayare>
those are some ideas... I hope they are helpful
< naywhayare>
I have to go to a meeting, but I'll be back later, and if you need help there is often someone in the channel who can help, or there is also the mlpack mailing list
< tarun_ml_enthusi>
in the machine learning course i was talking about i have implemented various algorithms as assignments
< tarun_ml_enthusi>
linear regression , logistic regressoin , k means etc.
< naywhayare>
yeah, but that's a bit different than implementing flexible, high-quality, fast implementations for use in a library like mlpack :)
< naywhayare>
I'll be back later...
< tarun_ml_enthusi>
oh okay ...yes i have signed up for the mailing list...ill take a closer look at the tutorials...thank you
tarun_ml_enthusi has quit [Quit: Page closed]
< zoq>
naywhayare: The download statistic is fascinating. I wonder which event triggered the last peak.
< naywhayare>
zoq: not sure, it would have been about two weeks ago
< naywhayare>
maybe something to do with the SE4ML workshop? but I don't think the word 'mlpack' is on their website anywhere
< naywhayare>
so it could just be random noise
< naywhayare>
http://mloss.org/software/downloadstats/152/ are the statistics as compiled by MLOSS (though I don't think that many people are downloading software through MLOSS anymore)
< naywhayare>
it shows a recent peak too; I wonder if it's the same one
< zoq>
yeah, I comared the results from mloss with the results your created from the server logs.
< naywhayare>
my logs don't pick up downloads where people installed the mlpack package from fedora/debian/ubuntu repos, though
< zoq>
maybe it is correlated with the k-means code you committed two weeks ago? I'm not sure
< naywhayare>
I doubt it; I don't think many people are watching the svn repo, but I suppose it's possible