Sciweavers

990 search results - page 118 / 198
» Using evolution strategies to solve DEC-POMDP problems
Sort
View
GECCO
2008
Springer
118views Optimization» more  GECCO 2008»
13 years 9 months ago
Unsupervised learning of echo state networks: balancing the double pole
A possible alternative to fine topology tuning for Neural Network (NN) optimization is to use Echo State Networks (ESNs), recurrent NNs built upon a large reservoir of sparsely r...
Fei Jiang, Hugues Berry, Marc Schoenauer
SI3D
2010
ACM
14 years 3 months ago
Volumetric obscurance
Obscurance and Ambient Occlusion (AO) are popular techniques in both film and games that model how ambient light is shadowed. While it is largely a solved problem for static scen...
Bradford James Loos, Peter-Pike Sloan
RAS
2006
134views more  RAS 2006»
13 years 8 months ago
Simultaneous planning, localization, and mapping in a camera sensor network
In this paper we examine issues of localization, exploration, and planning in the context of a hybrid robot/camera-network system. We exploit the ubiquity of camera networks to us...
Ioannis M. Rekleitis, David Meger, Gregory Dudek
GECCO
2005
Springer
100views Optimization» more  GECCO 2005»
14 years 1 months ago
Evolutionary tree genetic programming
We introduce a clustering-based method of subpopulation management in genetic programming (GP) called Evolutionary Tree Genetic Programming (ETGP). The biological motivation behin...
Ján Antolík, William H. Hsu
EOR
2006
79views more  EOR 2006»
13 years 8 months ago
Technology choice and timing with positive network effects
When two competing and incompatible products coexist in a market, potential users face a choice between the two products and the alternative of deferring the decision. This paper ...
Laura J. Kornish