Multilayer feedforward networks are universal approximators
Neural Networks
Advances in neural information processing systems 2
Selection of relevant features and examples in machine learning
Artificial Intelligence - Special issue on relevance
Wrappers for feature subset selection
Artificial Intelligence - Special issue on relevance
Model selection in neural networks
Neural Networks
An introduction to variable and feature selection
The Journal of Machine Learning Research
Dimensionality reduction via sparse support vector machines
The Journal of Machine Learning Research
Neural input selection-A fast model-based approach
Neurocomputing
Input selection for radial basis function networks by constrained optimization
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Analysis of fast input selection: application in time series prediction
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Avoiding Pitfalls in Neural Network Research
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Integrated feature architecture selection
IEEE Transactions on Neural Networks
Neural-network construction and selection in nonlinear modeling
IEEE Transactions on Neural Networks
Selecting useful features for personal credit risk analysis
International Journal of Business Information Systems
On calibration data selection: The case of stormwater quality regression models
Environmental Modelling & Software
Hi-index | 0.10 |
Choosing a useful combination of input variables and an appropriate complexity of the model is an essential task in nonlinear regression analysis because of the risk of overfitting. This article provides a workable solution for the multilayer perceptron model. An initial structure of the model, including all the input variables, is fixed in the beginning. Only the most useful input variables and hidden nodes remain effective when the model is fitted with the proposed penalization method. The method is tested on three benchmark data sets. Experimental results show that the removal of useless input variables and hidden nodes from the model improves its generalization capability. In addition, the proposed method compares favorably with respect to other penalization methods.