Sciweavers

683 search results - page 107 / 137
» Coarticulation in Markov Decision Processes
Sort
View
ICC
2007
IEEE
14 years 3 months ago
Dynamic Lightpath Establishment for Service Differentiation Based on Optimal MDP Policy in All-Optical Networks with Wavelength
— In this paper, we propose a dynamic lightpath establishment method for service differentiation in all-optical WDM networks with the capability of full-range wavelength conversi...
Takuji Tachibana, Shoji Kasahara, Kenji Sugimoto
ATAL
2004
Springer
14 years 2 months ago
Unifying Temporal and Structural Credit Assignment Problems
Single-agent reinforcement learners in time-extended domains and multi-agent systems share a common dilemma known as the credit assignment problem. Multi-agent systems have the st...
Adrian K. Agogino, Kagan Tumer
ASPDAC
2007
ACM
93views Hardware» more  ASPDAC 2007»
14 years 29 days ago
Flow-Through-Queue based Power Management for Gigabit Ethernet Controller
- This paper presents a novel architectural mechanism and a power management structure for the design of an energy-efficient Gigabit Ethernet controller. Key characteristics of suc...
Hwisung Jung, Andy Hwang, Massoud Pedram
AAAI
1996
13 years 10 months ago
An Optimal Contracting Strategy in a Digital Library
Agents can benefit from contracting some of their tasks that cannot be performedby themselves or that can be performed moreefficiently by other agents. Developing an agent's ...
Sunju Park, Edmund H. Durfee
ICASSP
2011
IEEE
13 years 20 days ago
Informative dialect recognition using context-dependent pronunciation modeling
We propose an informative dialect recognition system that learns phonetic transformation rules, and uses them to identify dialects. A hidden Markov model is used to align referenc...
Nancy F. Chen, Wade Shen, Joseph P. Campbell, Pedr...