Sciweavers

1039 search results - page 147 / 208
» A Dynamic Voltage Scaling Algorithm for Dynamic Workloads
Sort
View
JMLR
2006
115views more  JMLR 2006»
13 years 9 months ago
Structured Prediction, Dual Extragradient and Bregman Projections
We present a simple and scalable algorithm for maximum-margin estimation of structured output models, including an important class of Markov networks and combinatorial models. We ...
Benjamin Taskar, Simon Lacoste-Julien, Michael I. ...
CDC
2010
IEEE
160views Control Systems» more  CDC 2010»
13 years 3 months ago
Adaptive bases for Q-learning
Abstract-- We consider reinforcement learning, and in particular, the Q-learning algorithm in large state and action spaces. In order to cope with the size of the spaces, a functio...
Dotan Di Castro, Shie Mannor
ICRA
2007
IEEE
110views Robotics» more  ICRA 2007»
14 years 3 months ago
A Reinforcement Learning Approach to Lift Generation in Flapping MAVs: Experimental Results
— In [17] we proposed an RL framework for control of flapping-wing MAVs. The algorithm has been discussed and simulation results using a quasi-steady model showed initial promis...
Mehran Motamed, Joseph Yan
INFOCOM
2012
IEEE
11 years 11 months ago
Estimators also need shared values to grow together
—Network management applications require large numbers of counters in order to collect traffic characteristics for each network flow. However, these counters often barely fit ...
Erez Tsidon, Iddo Hanniel, Isaac Keslassy
DAC
2005
ACM
14 years 10 months ago
Net weighting to reduce repeater counts during placement
We demonstrate how to use placement to ameliorate the predicted repeater explosion problem caused by poor interconnect scaling. We achieve repeater count reduction by dynamically ...
Brent Goplen, Prashant Saxena, Sachin S. Sapatneka...