—This paper presents a new scalable buffer-management scheme for IP Differentiated Services. The scheme consists of a Differentiated Random Drop (DRD) algorithm using feedback fr...
d abstract) John Kececioglu and Dean Starrett Department of Computer Science The University of Arizona Tucson AZ 85721, USA A basic computational problem that arises in both the...
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 ...
Dynamically reconfigurable systems are known to have many advantages such as area and power reduction. The drawbacks of these systems are the reconfiguration delay and the overhead...
Nele Mentens, Benedikt Gierlichs, Ingrid Verbauwhe...
We present a new and efficient semi-supervised training method for parameter estimation and feature selection in conditional random fields (CRFs). In real-world applications suc...