Sciweavers

1474 search results - page 40 / 295
» Computing stable models: worst-case performance estimates
Sort
View
IJON
2000
61views more  IJON 2000»
13 years 7 months ago
Encoding multiple orientations in a recurrent network
Models containing recurrent connections amongst the cells within a population can account for a range of empirical data on orientation selectivity in striate cortex. However, exis...
Richard S. Zemel, Jonathan Pillow
JMM2
2006
167views more  JMM2 2006»
13 years 7 months ago
Computer Vision Methods for Improved Mobile Robot State Estimation in Challenging Terrains
External perception based on vision plays a critical role in developing improved and robust localization algorithms, as well as gaining important information about the vehicle and ...
Annalisa Milella, Giulio Reina, Roland Siegwart
ICASSP
2010
IEEE
13 years 2 months ago
Performance of shockwave-based shooter localization under model misspecification
This paper considers the estimation of shooter locations using a sensor network where each sensor measures the time difference between receptions of a firearm's muzzle blast ...
Joshua N. Ash, Gene T. Whipps, Richard J. Kozick
NECO
2007
129views more  NECO 2007»
13 years 7 months ago
Variational Bayes Solution of Linear Neural Networks and Its Generalization Performance
It is well-known that, in unidentifiable models, the Bayes estimation provides much better generalization performance than the maximum likelihood (ML) estimation. However, its ac...
Shinichi Nakajima, Sumio Watanabe
PPSN
1998
Springer
13 years 12 months ago
Mechanisms of Emergent Computation in Cellular Automata
Abstract. We introduce a class of embedded-particle models for describing the emergent computational strategies observed in cellular automata (CAs) that were evolved for performing...
Wim Hordijk, James P. Crutchfield, Melanie Mitchel...