Are there an open tools for solving HMMs for large datasets? i.e. if I have millions of observations from millions of users and want to learn a HMM from the data, what are my options?
http://mlpack.org/docs/mlpack-2.0.1/man/mlpack_hmm_generate....
http://mlpack.org/docs/mlpack-2.0.1/man/mlpack_hmm_train.htm...
http://mlpack.org/docs/mlpack-2.0.1/man/mlpack_hmm_loglik.ht...
http://mlpack.org/docs/mlpack-2.0.1/man/mlpack_hmm_viterbi.h...
There is also the HTK toolkit, but last I used that, years ago, I was pretty disappointed; it did not compile on a 64-bit system. Both of these are single-machine toolkits, so there is a limit to how much you can scale, but I think you may be able to deal with a million or so points with mlpack. There's also MATLAB's implementation, but that is not very fast.