Sciweavers

134 search results - page 6 / 27
» An Evolutionary Approach for Tuning Artificial Neural Networ...
Sort
View
CEC
2008
IEEE
14 years 1 months ago
Creating edge detectors by evolutionary reinforcement learning
— In this article we present results from experiments where a edge detector was learned from scratch by EANT2, a method for evolutionary reinforcement learning. The detector is c...
Nils T. Siebel, Sven Grünewald, Gerald Sommer
AES
2007
Springer
78views Cryptology» more  AES 2007»
13 years 7 months ago
Reliability and performance-based design by artificial neural network
Whilst conventional approach in structural design is based on reliability-calibrated factored design formula, performance-based design customizes a solution to the specific circum...
K. W. Chau
IJCNN
2007
IEEE
14 years 1 months ago
Parameter Optimization of PSS Based on Estimated Hessian Matrix from Trajectory Sensitivities
This paper describes the optimal tuning for the output limits of the power system stabilizer (PSS), which can improve the system damping performance immediately following a large d...
Seung-Mook Baek, Jung-Wook Park, Ganesh K. Venayag...
ICDAR
2003
IEEE
14 years 19 days ago
A Neural-Evolutionary Approach for Feature and Architecture Selection in Online Handwriting Recognition
An automatic recognition of online handwritten text has been an on-going research problem for nearly four decades. It has been gaining more interest due to the increasing populari...
Brijesh Verma, Moumita Ghosh
EUROGP
2004
Springer
170views Optimization» more  EUROGP 2004»
13 years 11 months ago
Comparing Hybrid Systems to Design and Optimize Artificial Neural Networks
Abstract. In this paper we conduct a comparative study between hybrid methods to optimize multilayer perceptrons: a model that optimizes the architecture and initial weights of mul...
Pedro A. Castillo Valdivieso, Maribel Garcí...