Re:SideCar's Kalman Filter models San Francisco brunch
by michaelmior on Thursday March 06, 2014 @08:37AM
(#7353536)
I don't have much knowledge of Kalman filters, but the Wikipedia article[1] claims the assumption of Gaussian error is a common misconception. A quick skim of the original paper[2] seems to confirm this.
[1] http://en.wikipedia.org/wiki/Kalman_filter
[2] http://www.cs.unc.edu/~welch/kalman/media/pdf/Kalman1960.pdf
Re:SideCar's Kalman Filter models San Francisco brunch
by gpcz on Thursday March 06, 2014 @10:26AM
(#7354189)
I didn't know that -- that's very interesting! Thank you for showing me that.
I learned about Kalman filters in a mobile robotics course that made explicit Gaussian assumptions early on for the primary topic (SqrtSAM), and they brought up Kalman filters in its own lecture as kind of a "this is how they used to do SLAM" lecture. Considering the large amount of overlap in the methods, such as the use of linear covariance projections, I guess I made the assumption that Kalman filters had the same Gaussian assumption.
Re:SideCar's Kalman Filter models San Francisco brunch
by michaelmior on Thursday March 06, 2014 @12:01PM
(#7354938)
Sounds like a pretty interesting course. Really I know about Kalman filters is the use case.
Re:SideCar's Kalman Filter models San Francisco brunch
by tel on Wednesday March 05, 2014 @08:45PM
(#7351312)
It sounded a lot like the interviewer didn't have enough expertise to do much over key of "Kalman filter" as sounding vaguely big data-ey. Too bad.
Re:SideCar's Kalman Filter models San Francisco brunch
by gpcz on Wednesday March 05, 2014 @09:33PM
(#7351499)
That may be a part of it. The problem was only described in vague terms, so there's probably a reason why a Kalman filter makes sense, but as it was described in the interview it seemed more like a regression problem to me.
Although the Kalman filter retains some aggregate data about past states in its iterated covariance estimate, it is still primarily a recurrence relation where the future state depends on the immediate present, much like a discretized low-pass filter. This is part of why I'm intrigued by the parent article's use of a Kalman filter for this application.