Sciweavers

6546 search results - page 891 / 1310
» Improving the Performance of the RISE Algorithm
Sort
View
SIGIR
2010
ACM
15 years 11 months ago
Adaptive near-duplicate detection via similarity learning
In this paper, we present a novel near-duplicate document detection method that can easily be tuned for a particular domain. Our method represents each document as a real-valued s...
Hannaneh Hajishirzi, Wen-tau Yih, Aleksander Kolcz
FCCM
2009
IEEE
134views VLSI» more  FCCM 2009»
15 years 11 months ago
Efficient Mapping of Hardware Tasks on Reconfigurable Computers Using Libraries of Architecture Variants
Scheduling and partitioning of task graphs on reconfigurable hardware needs to be carefully carried out in order to achieve the best possible performance. In this paper, we demons...
Miaoqing Huang, Vikram K. Narayana, Tarek A. El-Gh...
ATAL
2006
Springer
15 years 11 months ago
Probabilistic policy reuse in a reinforcement learning agent
We contribute Policy Reuse as a technique to improve a reinforcement learning agent with guidance from past learned similar policies. Our method relies on using the past policies ...
Fernando Fernández, Manuela M. Veloso
BIOADIT
2006
Springer
15 years 11 months ago
Proposal and Evaluation of a Cooperative Mechanism for Pure P2P File Sharing Networks
To provide application-oriented network services, a variety of overlay networks are deployed over physical IP networks. Since they share and compete for the same physical network r...
Junjiro Konishi, Naoki Wakamiya, Masayuki Murata
NAA
2000
Springer
125views Mathematics» more  NAA 2000»
15 years 11 months ago
Matrix Computations Using Quasirandom Sequences
Abstract. The convergence of Monte Carlo method for numerical integration can often be improved by replacing pseudorandom numbers (PRNs) with more uniformly distributed numbers kno...
Michael Mascagni, Aneta Karaivanova