A functions localized neural network with branch gates
Neural Networks
Feedforward Neural Network Construction Using Cross Validation
Neural Computation
Variations of the two-spiral task
Connection Science
A New Constructive Algorithm for Designing and Training Artificial Neural Networks
Neural Information Processing
Permutation Free Encoding Technique for Evolving Neural Networks
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks
Novel maximum-margin training algorithms for supervised neural networks
IEEE Transactions on Neural Networks
A novel similarity-based crossover for artificial neural network evolution
PPSN'10 Proceedings of the 11th international conference on Parallel problem solving from nature: Part I
Selection of weights for sequential feed-forward neural networks: an experimental study
IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems
Hi-index | 0.00 |
Constructive algorithms have proved to be powerful methods for training feedforward neural networks. An important property of these algorithms is generalization. A series of empirical studies were performed to examine the effect of regularization on generalization in constructive cascade algorithms. It was found that the combination of early stopping and regularization resulted in better generalization than the use of early stopping alone. A cubic penalty term that greatly penalizes large weights was shown to be beneficial for generalization in cascade networks. An adaptive method of setting the regularization magnitude in constructive algorithms was introduced and shown to produce generalization results similar to those obtained with a fixed, user-optimized regularization setting. This adaptive method also resulted in the construction of smaller networks for more complex problems. The acasper algorithm, which incorporates the insights obtained from the empirical studies, was shown to have good generalization and network construction properties. This algorithm was compared to the cascade correlation algorithm on the Proben 1 and additional regression data sets