Highly Influenced

# Neural network regularization and ensembling using multi-objective evolutionary algorithms

@article{Jin2004NeuralNR, title={Neural network regularization and ensembling using multi-objective evolutionary algorithms}, author={Yaochu Jin and Tatsuya Okabe and Bernhard Sendhoff}, journal={Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753)}, year={2004}, volume={1}, pages={1-8 Vol.1} }

- Published 2004 in Proceedings of the 2004 Congress on Evolutionary…
DOI:10.1109/CEC.2004.1330830

Regularization is an essential technique to improve generalization of neural networks. Traditionally, regularization is conducted by including an additional term in the cost function of a learning algorithm. One main drawback of these regularization techniques is that a hyperparameter that determines to which extension the regularization influences the learning algorithm must be determined beforehand. This paper addresses the neural network regularization problem from a multi-objective… CONTINUE READING

Highly Cited

This paper has 278 citations. REVIEW CITATIONS

#### 16 Figures & Tables

#### Topics

#### Statistics

Citations per Year

#### 279 Citations

Semantic Scholar estimates that this publication has

**279**citations based on the available data.See our **FAQ** for additional information.