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
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...
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 ...
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...
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...