Sciweavers

401 search results - page 26 / 81
» Evolving a neural network using dyadic connections
Sort
View
CEC
2009
IEEE
14 years 2 months ago
HyperNEAT controlled robots learn how to drive on roads in simulated environment
Abstract— In this paper we describe simulation of autonomous robots controlled by recurrent neural networks, which are evolved through indirect encoding using HyperNEAT algorithm...
Jan Drchal, Jan Koutník, Miroslav Snorek
ESWA
2006
154views more  ESWA 2006»
13 years 7 months ago
Artificial neural networks with evolutionary instance selection for financial forecasting
In this paper, I propose a genetic algorithm (GA) approach to instance selection in artificial neural networks (ANNs) for financial data mining. ANN has preeminent learning abilit...
Kyoung-jae Kim
CEC
2007
IEEE
13 years 11 months ago
Topology management in unstructured P2P networks using neural networks
Abstract-- Resource discovery is an essential problem in peerto-peer networks since there is no centralized index in which to look for information about resources. In a pure P2P ne...
Annemari Auvinen, Teemu Keltanen, Mikko Vapa
PPSN
2010
Springer
13 years 6 months ago
Indirect Encoding of Neural Networks for Scalable Go
Abstract. The game of Go has attracted much attention from the artificial intelligence community. A key feature of Go is that humans begin to learn on a small board, and then incr...
Jason Gauci, Kenneth O. Stanley
ESANN
2000
13 years 9 months ago
A comparative design of a MIMO neural adaptive rate damping for a nonlinear helicopter model
Using a nonlinear 15-state helicopter model in 6 DOF, two di erent neural control systems, both acting as rate damping, have been designed and compared. They are both based on the ...
Piero A. Gili, Manuela Battipede