Sciweavers

867 search results - page 112 / 174
» Optimizing synthesis with metasketches
Sort
View
GECCO
2011
Springer
276views Optimization» more  GECCO 2011»
14 years 4 months ago
Evolution of reward functions for reinforcement learning
The reward functions that drive reinforcement learning systems are generally derived directly from the descriptions of the problems that the systems are being used to solve. In so...
Scott Niekum, Lee Spector, Andrew G. Barto
CDC
2008
IEEE
121views Control Systems» more  CDC 2008»
15 years 7 months ago
Convex relaxations for quadratic distance problems
This paper deals with convex relaxations for quadratic distance problems, a class of optimization problems relevant to several important topics in the analysis and synthesis of ro...
Andrea Garulli, Alfio Masi, Antonio Vicino
93
Voted
ISVLSI
2005
IEEE
69views VLSI» more  ISVLSI 2005»
15 years 6 months ago
Pipelined Memory Controllers for DSP Applications Handling Unpredictable Data Accesses
Multimedia applications are often characterized by a large number of data accesses with regular and periodic access patterns. In these cases, optimized pipelined memory access con...
Bertrand Le Gal, Emmanuel Casseau, Sylvain Huet, E...
100
Voted
GECCO
2005
Springer
15 years 6 months ago
Function choice, resiliency and growth in genetic programming
In this paper we examine how the choice of functions in a genetic program (GP) affects the rate of code growth and the development of resilient individuals. We find that functio...
Sireesha Besetti, Terence Soule
ISVLSI
2002
IEEE
116views VLSI» more  ISVLSI 2002»
15 years 5 months ago
Multi-Output Timed Shannon Circuits
Timed Shannon circuits have been proposed as a synthesis approach for a low power optimization technique at the logic level since overall circuit switching probabilities may be re...
Mitchell A. Thornton, Rolf Drechsler, D. Michael M...