Sciweavers

TNN
2010
185views Management» more  TNN 2010»
12 years 9 months ago
An adaptive multiobjective approach to evolving ART architectures
In this paper, we present the evolution of adaptive resonance theory (ART) neural network architectures (classifiers) using a multiobjective optimization approach. In particular, w...
Assem Kaylani, Michael Georgiopoulos, Mansooreh Mo...
APIN
2004
116views more  APIN 2004»
13 years 2 months ago
Neural Learning from Unbalanced Data
This paper describes the result of our study on neural learning to solve the classification problems in which data is unbalanced and noisy. We conducted the study on three differen...
Yi Lu Murphey, Hong Guo, Lee A. Feldkamp
IJON
2008
116views more  IJON 2008»
13 years 2 months ago
Evolutionary ensemble of diverse artificial neural networks using speciation
Recently, many researchers have designed neural network architectures with evolutionary algorithms but most of them have used only the fittest solution of the last generation. To ...
Kyung-Joong Kim, Sung-Bae Cho
FLAIRS
2000
13 years 3 months ago
Comparing Performance of Neural Networks Applied to a Simplified Recognition Problem
In this note we present and discuss results of experiments comparing the performance of six neural network architectures (back propagation, recurrent network with dampened feedbac...
Marcin Paprzycki, Rick Niess, Jason Thomas, Lenny ...
ICONIP
2007
13 years 3 months ago
Diverse Evolutionary Neural Networks Based on Information Theory
There is no consensus on measuring distances between two different neural network architectures. Two folds of methods are used for that purpose: Structural and behavioral distance ...
Kyung-Joong Kim, Sung-Bae Cho
CEC
2008
IEEE
13 years 4 months ago
Efficient evolution of ART neural networks
Abstract-- Genetic algorithms have been used to evolve several neural network architectures. In a previous effort, we introduced the evolution of three well known ART architects; F...
Assem Kaylani, Michael Georgiopoulos, Mansooreh Mo...
ICANN
2009
Springer
13 years 7 months ago
Scalable Neural Networks for Board Games
Learning to solve small instances of a problem should help in solving large instances. Unfortunately, most neural network architectures do not exhibit this form of scalability. Our...
Tom Schaul, Jürgen Schmidhuber