Sciweavers

5864 search results - page 294 / 1173
» Can We Work around Numerical Methods
Sort
View
IROS
2007
IEEE
175views Robotics» more  IROS 2007»
16 years 1 months ago
Simulation and weights of multiple cues for robust object recognition
Reliable recognition of objects is an important capabaility in the progress towards getting agents to accomplish and assist in a variety of useful tasks such as search and rescue ...
Sarah Aboutalib, Manuela M. Veloso
SIAMADS
2010
100views more  SIAMADS 2010»
15 years 2 months ago
Optimal Intrinsic Dynamics for Bursting in a Three-Cell Network
Previous numerical and analytical work has shown that synaptic coupling can allow a network of model neurons to synchronize despite heterogeneity in intrinsic parameter values. In ...
Justin R. Dunmyre, Jonathan E. Rubin
217
Voted
TC
1998
15 years 7 months ago
Methodologies for Tolerating Cell and Interconnect Faults in FPGAs
—The very high levels of integration and submicron device sizes used in current and emerging VLSI technologies for FPGAs lead to higher occurrences of defects and operational fau...
Fran Hanchek, Shantanu Dutt
209
Voted
ICML
2009
IEEE
16 years 8 months ago
Large-scale deep unsupervised learning using graphics processors
The promise of unsupervised learning methods lies in their potential to use vast amounts of unlabeled data to learn complex, highly nonlinear models with millions of free paramete...
Rajat Raina, Anand Madhavan, Andrew Y. Ng
177
Voted
ICASSP
2011
IEEE
14 years 11 months ago
Dictionary learning of convolved signals
Assuming that a set of source signals is sparsely representable in a given dictionary, we show how their sparse recovery fails whenever we can only measure a convolved observation...
Daniele Barchiesi, Mark D. Plumbley