These are chat archives for bayespy/bayespy

16th
Oct 2017
eykiriku
@eykiriku
Oct 16 2017 13:51
Assume I have an observation node that instead of being Categorical like the activity node here (http://bayespy.org/examples/hmm.html), it represents the degree of activation of fuzzy rules: 80% walk and 20% shop are active. What node model should I use instead of Categorical to allow inference with observations that result from fuzzy sets?
Jaakko Luttinen
@jluttine
Oct 16 2017 13:57
do you mean that you're knowledge about whether walk or shop is p(walk)=0.8 and p(shop)=0.2, or what is the meaning of those percentages?
eykiriku
@eykiriku
Oct 16 2017 13:58
Capture.PNG
say this graph is yawning frequency per minute, my input is approx. 2.5 yawning per minute which will have a 80% activation of the high rule and 20% of the normal rule
in short, yes you were right
Jaakko Luttinen
@jluttine
Oct 16 2017 14:04
if you observe probabilities, maybe one can use beta or dirichlet node. if you have noisy observations of a categorical variable, maybe you can add a noisy observed categorical variable that has the true (unknown) state as a parent.
s/probabilities/probabilities or some other variables that are positive and sum to one/
eykiriku
@eykiriku
Oct 16 2017 14:05
true, thanks
eykiriku
@eykiriku
Oct 16 2017 15:40
my problem was more related to bayespy, like assume i choose a dirichlet observation node Y. Y has 2 states, Normal and High. As above, any evidence will belong to the array [0, 5] and the fuzzy rules may lead to an output saying 80% activation of high and 20%.... My doubt is how to define the variable 'activity', the one to be observed for inference in Y.observe(activity), using this fuzzy ouput