GLOBAL OPTIMIZATION METHODS

Training a neural network is a difficult optimization problem because of numerous local minimums. Many global search algorithms have been used to train neural networks. However, local search algorithms are more efficient with computational resources, and therefore numerous random restarts with a local algorithm may be more effective than a global algorithm. This study uses Monte-Carlo simulations to determine the relative efficiency of a local search algorithm to 9 stochastic global algorithms. The computational requirements of the global algorithms are several times higher than the local algorithm and there is little gain in using the global algorithms to train neural networks.


Issue Date:
2002
Publication Type:
Conference Paper/ Presentation
PURL Identifier:
http://purl.umn.edu/36631
Total Pages:
23
Series Statement:
Selected Paper of the 2002 Annual Meeting, July 28-31, 2002, Long Beach, California




 Record created 2017-04-01, last modified 2017-05-15

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)