Interested in contributing - Bayesian Classifier?

[tedkornish]

Hey Mike,

I'm interested in contributing as a fun exercise for my ML and Haskell chops. A disclaimer: I don't have a strong background in machine learning implementations and I haven't been writing Haskell for more than a few months. However, I'm willing to work hard, read papers and learn the ropes.

It looks like HLearn is currently lacking a Naive Bayesian Classifier implementation - do you think that would make a good initial project?

Cheers,
T

[mikeizbicki]

Hi Ted.

Actually, HLearn used to have a Naive Bayes implementation, but I've temporarily removed it. I'm not happy with the current way Haskell handles random variables/distribution like things, and one of my future goals with HLearn is to have a more mathematically sound interface. So thanks for the interest, but I don't think this is a good intro project.

A better intro project would be to implement a new optimization method. The optimization interface is getting pretty well fleshed out, and other people have had some success contributing in this way.

[tedkornish]

Sounds good. I'll poke around the Git history and see what other people have contributed, then do some reading and try to pick a good diving-off point. Before I start, I'll probably shoot you an email to make sure that what I'm working on is productive and useful to the library.

Thanks!

[mikeizbicki]

The dbrent method for univariate optimization is what I had in mind when I said that.

[tedkornish]

Solid! That sounds like a great start.