zhongwen opened this issue 10 years ago · 1 comments
Both the codes in the function _step(m_, x_, h_, c_) from here and in computing state_below from here add the bias term, which seems to be wrong. Could you please have a look? Or if it is correct, could you please explain it a bit? Thx.
_step(m_, x_, h_, c_)
state_below
Yeah this is an unnecessary add. I noticed it later but I forgot to fix it here. It shouldn't change the results but thanks for pointing it out!