Authors: Wu, Lizhong; Moody, John
Source: Neural Computation, Vol. 7, 1995
Click to receive a postscript copy of the paper via FTP
We derive a smoothing regularizer for dynamic network models by requiring robustness in prediction performance to perturbations of the training data. The regularizer can be viewed as a generalization of the first order Tikhonov stabilizer to dynamic models. We have successfully tested this regularizer in a number of case studies and found that it performs better than standard quadratic weight decay.
NeuroSolutions Home Page