TD-Gammon is a neural network that is able to teach itself to play backgammon solely by playing against itself and learning from the results. Starting from random initial play, TD...
Anticipatory algorithms for online stochastic optimization have been shown very effective in a variety of areas, including logistics, reservation systems, and scheduling. For such ...
Abstract. This paper introduces a new technique called adaptive elitistpopulation search method for allowing unimodal function optimization methods to be extended to efficiently lo...
Software synthesis from a concurrent functional specification is a key problem in the design of embedded systems. A concurrent specification is well-suited for medium-grained part...
This paper presents a very efficient algorithm for performance-driven topology design for interconnects. Given a net, it first generates A-tree1 topology using table lookup and net...