Content deleted Content added
m →Merge with BCJR algorithm: closing |
|||
Line 4:
==Untitled==
The O_1 matrix listed in the Forward Algorithm section is inconsistent with the one presented in the Example section, even though both the transition matrix (T) and the emission matrix (B) are the same between the two sections. I believe the O_1 matrix listed in the example section is correct. This would be much more clear if there were more hidden states than emissions or vice versa, since the matrix dimensions would be indicative of whether states are being conditioned on emissions or if emissions are being conditioned on states. No edits made.
---
The description is very hard to follow. It is incomplete, being based upon and making reference to a book that is not available online. The one-dimensional vectors are written wrongly in the matrix formulas (horizontal instead of vertical). IMO, this article needs a fundamental re-writing, it is extremely frustrating to read as it is.
| |||