Sciweavers

401 search results - page 14 / 81
» Evolving a neural network using dyadic connections
Sort
View
GECCO
2005
Springer
175views Optimization» more  GECCO 2005»
14 years 1 months ago
Nonlinear feature extraction using a neuro genetic hybrid
Feature extraction is a process that extracts salient features from observed variables. It is considered a promising alternative to overcome the problems of weight and structure o...
Yung-Keun Kwon, Byung Ro Moon
SIGGRAPH
1994
ACM
13 years 11 months ago
Evolving virtual creatures
This paper describes a novel system for creating virtual creatures that move and behave in simulated three-dimensional physical worlds. The morphologies of creatures and the neura...
Karl Sims
IJON
2006
138views more  IJON 2006»
13 years 7 months ago
Time-series prediction using a local linear wavelet neural network
A local linear wavelet neural network (LLWNN) is presented in this paper. The difference of the network with conventional wavelet neural network (WNN) is that the connection weigh...
Yuehui Chen, Bo Yang, Jiwen Dong
CEC
2009
IEEE
14 years 2 months ago
Evolving modular neural-networks through exaptation
— Despite their success as optimization methods, evolutionary algorithms face many difficulties to design artifacts with complex structures. According to paleontologists, living...
Jean-Baptiste Mouret, Stéphane Doncieux
GECCO
2009
Springer
118views Optimization» more  GECCO 2009»
14 years 2 months ago
The impact of network topology on self-organizing maps
In this paper, we study instances of complex neural networks, i.e. neural networks with complex topologies. We use Self-Organizing Map neural networks whose neighborhood relations...
Fei Jiang, Hugues Berry, Marc Schoenauer