Skip to Main Content
ASME Press Select Proceedings

Intelligent Engineering Systems Through Artificial Neural Networks, Volume 17

Editor
C. H. Dagli
C. H. Dagli
Search for other works by this author on:
ISBN-10:
0791802655
No. of Pages:
650
Publisher:
ASME Press
Publication date:
2007

This paper introduces a new procedure for gradient-based training of multilayer perceptron neural networks to simultaneously approximate both a function and its first derivatives. It is assumed that the true function values and the true derivatives are available at the training points. An algorithm is then derived to compute the gradient of a new performance function that combines both squared function error and squared derivative error. Experimental results show that the neural networks trained by the new procedure yield more accurate approximations for both the functions and their first derivatives than networks trained by standard methods. In addition, it is shown that the generalization capabilities of networks trained using this new procedure are better than those trained with early stopping or Bayesian regularization, even though no validation set is used.

This content is only available via PDF.
Close Modal
This Feature Is Available To Subscribers Only

Sign In or Create an Account

Close Modal
Close Modal