Skip to Main Content
ASME Press Select Proceedings

Intelligent Engineering Systems through Artificial Neural Networks, Volume 16

Editor
Cihan H. Dagli
Cihan H. Dagli
Search for other works by this author on:
Anna L. Buczak
Anna L. Buczak
Search for other works by this author on:
David L. Enke
David L. Enke
Search for other works by this author on:
Mark Embrechts
Mark Embrechts
Search for other works by this author on:
Okan Ersoy
Okan Ersoy
Search for other works by this author on:
ISBN-10:
0791802566
No. of Pages:
1000
Publisher:
ASME Press
Publication date:
2006

A new exploratory self-adaptive derivative free training algorithm is developed. It only evaluates error function that is reduced to a set of sub-problems in a constrained search space and the search directions follow rectilinear moves. To accelerate the training algorithm, an interpolation search is developed that determines the best learning rates. The constrained interpolation search decides the best learning rates such that the direction of search is not deceived in locating the minimum trajectory of the error function.

The proposed algorithm is practical when the error function is ill conditioned implying that the Hessian matrix property is unstable, or the derivative evaluation is difficult. The benchmark XOR problem (Nitta, 2003) is used to compare the performance of the proposed algorithm with the standard back propagation training methods. The proposed algorithm improves over the standard first order back propagation training method in function evaluations by a factor of 32. The improvement in standard deviation for the same metric has a ratio of 38:1. This implies that the proposed algorithm has less intractable instances.

You do not currently have access to this chapter.
Close Modal
This Feature Is Available To Subscribers Only

Sign In or Create an Account

Close Modal
Close Modal