Genetic algorithms + data structures = evolution programs (3rd ed.)
Genetic algorithms + data structures = evolution programs (3rd ed.)
Evolutionary optimization of RBF networks
Radial basis function networks 1
Measuring lift quality in database marketing
ACM SIGKDD Explorations Newsletter - Special issue on “Scalable data mining algorithms”
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Feature Extraction, Construction and Selection: A Data Mining Perspective
Feature Extraction, Construction and Selection: A Data Mining Perspective
Feature Selection for Knowledge Discovery and Data Mining
Feature Selection for Knowledge Discovery and Data Mining
Data Mining and Knowledge Discovery with Evolutionary Algorithms
Data Mining and Knowledge Discovery with Evolutionary Algorithms
A Theory of Networks for Approximation and Learning
A Theory of Networks for Approximation and Learning
A GA-based RBF classifier with class-dependent features
CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02
Rule extraction from an RBF classifier based on class-dependent features
CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Feature selection and structure optimisation are two key tasks in many neural network applications. This article sets out an evolutionary algorithm (EA) that performs the two tasks simultaneously for radial basis function (RBF) networks. The algorithm selects appropriate input features from a given set of possible features and adapts the number of basis functions (hidden neurons). The feasibility and the benefits of this approach are demonstrated in a direct marketing application in the automotive industry: the selection of promising targets for a direct mailing campaign, i.e. people who are likely to buy a certain product (here: car of a certain make). The method is independent from the application example given so that the ideas and solutions may easily be transferred to other neural network paradigms.