Sciweavers

30 search results - page 4 / 6
» Overfitting and Neural Networks: Conjugate Gradient and Back...
Sort
View
GECCO
2004
Springer
103views Optimization» more  GECCO 2004»
13 years 11 months ago
Training Neural Networks with GA Hybrid Algorithms
Abstract. Training neural networks is a complex task of great importance in the supervised learning field of research. In this work we tackle this problem with five algorithms, a...
Enrique Alba, J. Francisco Chicano
CIG
2006
IEEE
13 years 11 months ago
A Coevolutionary Model for The Virus Game
— In this paper, coevolution is used to evolve Artificial Neural Networks (ANN) which evaluate board positions of a two player zero-sum game (The Virus Game). The coevolved neura...
Peter I. Cowling, M. H. Naveed, M. A. Hossain
TNN
2010
234views Management» more  TNN 2010»
13 years 13 days ago
Novel maximum-margin training algorithms for supervised neural networks
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
Oswaldo Ludwig, Urbano Nunes
IJCNN
2007
IEEE
14 years 1 days ago
Upper Bound on Pattern Storage in Feedforward Networks
—Starting from the strict interpolation equations for multivariate polynomials, an upper bound is developed for the number of patterns that can be memorized by a nonlinear feedfo...
Pramod Lakshmi Narasimha, Michael T. Manry, Franci...
ESANN
2003
13 years 7 months ago
Autonomous learning algorithm for fully connected recurrent networks
In this paper fully connected RTRL neural networks are studied. In order to learn dynamical behaviours of linear-processes or to predict time series, an autonomous learning algori...
Edouard Leclercq, Fabrice Druaux, Dimitri Lefebvre