Sciweavers

3031 search results - page 280 / 607
» Investigating human-computer optimization
Sort
View
ECML
2007
Springer
15 years 10 months ago
Nondeterministic Discretization of Weights Improves Accuracy of Neural Networks
Abstract. The paper investigates modification of backpropagation algorithm, consisting of discretization of neural network weights after each training cycle. This modification, a...
Marcin Wojnarski
GECCO
2005
Springer
111views Optimization» more  GECCO 2005»
15 years 10 months ago
XCS with eligibility traces
The development of the XCS Learning Classifier System has produced a robust and stable implementation that performs competitively in direct-reward environments. Although investig...
Jan Drugowitsch, Alwyn Barry
GECCO
2009
Springer
128views Optimization» more  GECCO 2009»
15 years 9 months ago
Evolving stochastic processes using feature tests and genetic programming
The synthesis of stochastic processes using genetic programming is investigated. Stochastic process behaviours take the form of time series data, in which quantities of interest v...
Brian J. Ross, Janine H. Imada
ICC
2007
IEEE
114views Communications» more  ICC 2007»
15 years 8 months ago
Channel-Matched Spreading Codes for the Downlink of MC-CDMA
Abstract-- This paper concerns the multiple access performance of spreading codes used in the downlink of multicarrier code-division multiple-access (MC-CDMA). Complex-valued sprea...
Qinghua Shi, Yong Liang Guan, Choi Look Law
GECCO
2006
Springer
159views Optimization» more  GECCO 2006»
15 years 8 months ago
Standard and averaging reinforcement learning in XCS
This paper investigates reinforcement learning (RL) in XCS. First, it formally shows that XCS implements a method of generalized RL based on linear approximators, in which the usu...
Pier Luca Lanzi, Daniele Loiacono