Sciweavers

2191 search results - page 373 / 439
» Improving the Efficiency of Non-Deterministic Computations
Sort
View
TNN
2008
138views more  TNN 2008»
13 years 9 months ago
A Fast and Scalable Recurrent Neural Network Based on Stochastic Meta Descent
This brief presents an efficient and scalable online learning algorithm for recurrent neural networks (RNNs). The approach is based on the real-time recurrent learning (RTRL) algor...
Zhenzhen Liu, Itamar Elhanany
TROB
2008
105views more  TROB 2008»
13 years 9 months ago
Robot-to-Robot Relative Pose Estimation From Range Measurements
In this paper, we address the problem of determining the 2D relative pose of pairs of communicating robots from (i) robot-to-robot distance measurements and (ii) displacement estim...
Xun S. Zhou, Stergios I. Roumeliotis
JMLR
2002
83views more  JMLR 2002»
13 years 8 months ago
On Online Learning of Decision Lists
A fundamental open problem in computational learning theory is whether there is an attribute efficient learning algorithm for the concept class of decision lists (Rivest, 1987; Bl...
Ziv Nevo, Ran El-Yaniv
SIAMJO
2002
122views more  SIAMJO 2002»
13 years 8 months ago
Robust Filtering via Semidefinite Programming with Applications to Target Tracking
In this paper we propose a novel finite-horizon, discrete-time, time-varying filtering method based on the robust semidefinite programming (SDP) technique. The proposed method prov...
Lingjie Li, Zhi-Quan Luo, Timothy N. Davidson, Kon...
TCSV
2002
78views more  TCSV 2002»
13 years 8 months ago
Local bandwidth constrained fast inverse motion compensation for DCT-domain video transcoding
DCT-based digital video coding standards such as MPEG and H.26x are becoming more widely adopted for multimedia applications. Since the standards differ in their format and syntax...
Shizhong Liu, Alan C. Bovik