M
Mark A. Paskin
Researcher at University of California, Berkeley
Publications - 20
Citations - 1578
Mark A. Paskin is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Inference & Wireless sensor network. The author has an hindex of 15, co-authored 20 publications receiving 1566 citations. Previous affiliations of Mark A. Paskin include Stanford University & IBM.
Papers
More filters
Proceedings ArticleDOI
Distributed regression: an efficient framework for modeling sensor network data
TL;DR: An evaluation of the algorithm based upon data from a 48-node sensor network deployment at the Intel Research - Berkeley Lab is presented, demonstrating that the distributed algorithm converges to the optimal solution at a fast rate and is very robust to packet losses.
Proceedings Article
Thin junction tree filters for simultaneous localization and mapping
TL;DR: A linear-space filter is presented that maintains a tractable approximation of the belief state as a thin junction tree and is periodically "thinned" to remain tractable.
Proceedings Article
Linear-time inference in Hierarchical HMMs
Kevin Murphy,Mark A. Paskin +1 more
TL;DR: This paper shows how HHMMs are a special kind of dynamic Bayesian network (DBN), and thereby derive a much simpler inference algorithm, which only takes O(T) time.
Proceedings ArticleDOI
A robust architecture for distributed inference in sensor networks
TL;DR: Experimental results from a prototype implementation on a 97-node Mica2 mote network, as well as simulation results for three applications: distributed sensor calibration, optimal control, and sensor field modeling, demonstrate that the distributed architecture presented can solve many important inference problems exactly, efficiently, and robustly.
Proceedings ArticleDOI
Distributed localization of networked cameras
TL;DR: A fully distributed approach for camera network calibration that scales easily to very large camera networks and requires minimal overlap of the cameras' fields of view and makes very few assumptions about the motion of the object.