Skip to main content
MathOverflow

Timeline for How can the Kalman filter be adapted to handle binary observations?

Current License: CC BY-SA 3.0

15 events
when toggle format what by license comment
May 5, 2023 at 14:21 answer added NiceStats timeline score: 1
S Dec 19, 2016 at 15:07 history suggested Rodrigo de Azevedo
added tag to question
Dec 19, 2016 at 14:26 review Suggested edits
S Dec 19, 2016 at 15:07
Dec 12, 2016 at 1:30 comment added 8one6 Well, as per above, we're good on the locally linear model for the hidden variable. But the whole point is to discuss a highly non-normal model for the noise on the observation process.
Dec 11, 2016 at 18:30 comment added reuns The extended Kalman filter works for any smooth (locally linear) generative model for your data, with the assumption of a gaussian and decorrelated noise.
Dec 10, 2016 at 13:02 answer added ofer zeitouni timeline score: 4
Dec 8, 2016 at 16:43 answer added Jean Duchon timeline score: 1
S Dec 8, 2016 at 13:41 history suggested Rodrigo de Azevedo
added tag to question
Dec 8, 2016 at 13:40 answer added Roger Labbe timeline score: 2
Dec 8, 2016 at 13:24 review Suggested edits
S Dec 8, 2016 at 13:41
Dec 8, 2016 at 5:27 comment added passerby51 @8none6, there is a general algorithm called sum-product (or max-product) or belief propagation, generalizing Kalman filters. See for example. What you describe sounds like a hidden markov model with a discrete observation, and you can use sum-product in this case too.
Dec 7, 2016 at 23:17 comment added AHusain @RodrigodeAzevedo Could work around with log-likelihood. Can we get away with (0,1) instead?
S Dec 7, 2016 at 22:14 history suggested Rodrigo de Azevedo CC BY-SA 3.0
minor edits
Dec 7, 2016 at 21:56 review Suggested edits
S Dec 7, 2016 at 22:14
Dec 7, 2016 at 21:23 history asked 8one6 CC BY-SA 3.0