[mlpack-git] [mlpack] HMM simple example (#470)

Ryan Curtin notifications at github.com
Mon Nov 16 10:31:11 EST 2015


Ah, sorry, you're right.  I forgot about that restriction.  At the moment the `DiscreteDistribution` class only works with one-dimensional observations.  Realistically you can just transform your discrete observations to one dimension without any change in the model... if you have two dimensions that each take values between 0 and 9, then you could have one dimension that takes values between 00 and 99 (just concatenate the two dimensions).  This will give you the same HMM in the end.

It'd be possible to extend support for the discrete distribution to multiple dimensions more directly, but that hasn't been done at this time.

Anyway, you shouldn't have the problem with Gaussian or GMM HMMs.

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/issues/470#issuecomment-157068293
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20151116/c263d181/attachment.html>


More information about the mlpack-git mailing list