Sciweavers

1085 search results - page 94 / 217
» On the performance of one-to-many data transformations
Sort
View
MICAI
2009
Springer
14 years 3 months ago
A Two-Stage Relational Reinforcement Learning with Continuous Actions for Real Service Robots
Reinforcement Learning is a commonly used technique in robotics, however, traditional algorithms are unable to handle large amounts of data coming from the robot’s sensors, requi...
Julio H. Zaragoza, Eduardo F. Morales
ICIP
2005
IEEE
14 years 10 months ago
Comparison of invariant descriptors for object recognition
This paper deals with the performance evaluation of three object invariant descriptors : Hu moments, Zernike moments and Fourier-Mellin descriptors. Experiments are conducted on a...
Anant Choksuriwong, Bruno Emile, Hélè...
PLDI
2004
ACM
14 years 2 months ago
Cost effective dynamic program slicing
Although dynamic program slicing was first introduced to aid in user level debugging, applications aimed at improving software quality, reliability, security, and performance hav...
Xiangyu Zhang, Rajiv Gupta
IEEEPACT
2002
IEEE
14 years 2 months ago
Increasing and Detecting Memory Address Congruence
A static memory reference exhibits a unique property when its dynamic memory addresses are congruent with respect to some non-trivial modulus. Extraction of this congruence inform...
Samuel Larsen, Emmett Witchel, Saman P. Amarasingh...
SIGPRO
2010
137views more  SIGPRO 2010»
13 years 7 months ago
Satellite image compression by post-transforms in the wavelet domain
This paper proposes a novel compression scheme with a tunable complexity-ratedistortion trade-off. As images increase in size and resolution, more efficient compression schemes w...
Xavier Delaunay, Marie Chabert, Vincent Charvillat...