Sciweavers

20673 search results - page 421 / 4135
» Improving Performance on the Internet
Sort
View
ATAL
2009
Springer
15 years 11 months ago
Improved approximation of interactive dynamic influence diagrams using discriminative model updates
Interactive dynamic influence diagrams (I-DIDs) are graphical models for sequential decision making in uncertain settings shared by other agents. Algorithms for solving I-DIDs fac...
Prashant Doshi, Yifeng Zeng
ICASSP
2009
IEEE
15 years 10 months ago
Improved clustered hierarchical tandem system with bottom-up processing
The outputs of multi-layer perceptron (MLP) classifiers have been successfully used in tandem systems as features for HMM-based automatic speech recognition. In a previous paper, ...
Shuo-Yiin Chang, Lin-Shan Lee
ROBOCUP
2000
Springer
130views Robotics» more  ROBOCUP 2000»
15 years 10 months ago
Improvement Continuous Valued Q-learning and Its Application to Vision Guided Behavior Acquisition
Q-learning, a most widely used reinforcement learning method, normally needs well-defined quantized state and action spaces to converge. This makes it difficult to be applied to re...
Yasutake Takahashi, Masanori Takeda, Minoru Asada
MICRO
1995
IEEE
217views Hardware» more  MICRO 1995»
15 years 10 months ago
Improving instruction-level parallelism by loop unrolling and dynamic memory disambiguation
Exploitation ofinstruction-levelparallelism is an ejfective mechanism for improving the performance of modern super-scalar/VLIW processors. Various software techniques can be appl...
Jack W. Davidson, Sanjay Jinturkar
CONEXT
2008
ACM
15 years 8 months ago
TCP improvement in multi-radio multi-channel multi-hop networks
In this paper, we seek to enhance the poor performance of original TCP in wireless multi-hop environments due to the intra-flow contention between TCP-DATA and TCP-ACK packets. As...
Xiaofei Wang, Taekyoung Kwon, Yanghee Choi