Sciweavers

4864 search results - page 1 / 973
» Evolving neural networks
Sort
View
ICANN
2010
Springer
13 years 3 months ago
Time Series Forecasting by Evolving Artificial Neural Networks Using "Shuffle", Cross-Validation and Ensembles
Accurate time series forecasting are important for several business, research, and application of engineering systems. Evolutionary Neural Networks are particularly appealing becau...
Juan Peralta, Germán Gutiérrez, Arac...
ECAL
2005
Springer
13 years 10 months ago
Analysing the Evolvability of Neural Network Agents Through Structural Mutations
This paper investigates evolvability of artificial neural networks within an artificial life environment. Five different structural mutations are investigated, including adaptive e...
Ehud Schlessinger, Peter J. Bentley, R. Beau Lotto
GECCO
2004
Springer
134views Optimization» more  GECCO 2004»
13 years 10 months ago
A Descriptive Encoding Language for Evolving Modular Neural Networks
Evolutionary algorithms are a promising approach for the automated design of artificial neural networks, but they require a compact and efficient genetic encoding scheme to repres...
Jae-Yoon Jung, James A. Reggia
IJCNN
2000
IEEE
13 years 9 months ago
Evolving Neural Network Structures Using Axonal Growth Mechanisms
In the eld of arti cial evolution creating methods to evolve neural networks is an important goal. But how to encode the structure and properties of the neural network in the geno...
Peter Eggenberger
ISNN
2004
Springer
13 years 10 months ago
Evolving Flexible Neural Networks Using Ant Programming and PSO Algorithm
A flexible neural network (FNN) is a multilayer feedforward neural network with the characteristics of: (1) overlayer connections; (2) variable activation functions for different...
Yuehui Chen, Bo Yang, Jiwen Dong