FAST toolkit for Hidden Markov Models with Features 1.2.1

Jose Gonzalez Brenes, Yun Huang — Tue, 28 Apr 2015 17:48:23 -0000

FAST, is an toolkit for adding features to Hidden Markov Models (HMM). It implements a recent variation of the Expectation-Maximization algorithm (Berg-Kirkpatrick et al, 2010) that allows to use logistic regression in unsupervised learning.

We demonstrate FAST for predicting future student performance. Our toolkit is up to 300x faster than BNT (a Bayesian Network toolkit), and up to 25% better than conventional HMMs (with no features).

Comment by Jose Gonzalez-Brenes on 2015-04-29 04:25

Jose Gonzalez-Brenes — Wed, 29 Apr 2015 04:25:23 -0000

We have a big update of FAST coming soon in terms of documentation and generalizability. The current implementation is optimized for student model.

We are uploading this preliminary version for now to be eligible to participate in the MLOSS workshop at ICML.

mloss.org FAST toolkit for Hidden Markov Models with Features

FAST toolkit for Hidden Markov Models with Features 1.2.1

Comment by Jose Gonzalez-Brenes on 2015-04-29 04:25