[mlpack] [mlpack/mlpack] HMM initialization: don't use equal initial probabilities. (#828)
Ryan Curtin
notifications at github.com
Mon Dec 12 14:45:29 EST 2016
That can cause training to fail sometimes. Instead, optimization seems to perform better when using random intiialization.
This is a fix that came out of some debugging in the IRC channel.
You can view, comment on, or merge this pull request online at:
https://github.com/mlpack/mlpack/pull/828
-- Commit Summary --
* Don't use equal initial probabilities.
-- File Changes --
M src/mlpack/methods/hmm/hmm_impl.hpp (11)
M src/mlpack/tests/hmm_test.cpp (5)
-- Patch Links --
https://github.com/mlpack/mlpack/pull/828.patch
https://github.com/mlpack/mlpack/pull/828.diff
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/828
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://knife.lugatgt.org/pipermail/mlpack/attachments/20161212/a4038964/attachment.html>
More information about the mlpack
mailing list