This paper presents a novel repeater insertion algorithm for the power minimization of realistic interconnect trees under given timing budgets. Our algorithm judiciously combines ...
In the model-based policy search approach to reinforcement learning (RL), policies are found using a model (or "simulator") of the Markov decision process. However, for ...
In this paper we introduce Ant-Q, a family of algorithms which present many similarities with Q-learning (Watkins, 1989), and which we apply to the solution of symmetric and asymm...
To automatically register foreground target in cluttered images, we present a novel hierarchical graph representation and a stochastic computing strategy in Bayesian framework. Th...
Xiaobai Liu, Liang Lin, Hongwei Li, Hai Jin, Wenbi...
Construction of overlay networks without any consideration of real network topologies causes inefficient routing in peer-to-peer networks. This paper presents the design and evalua...