Global optimization for neural network training

We propose a novel global minimization method, called NOVEL (Nonlinear Optimization via External Lead), and demonstrate its superior performance on neural network learning problems. The goal is improved learning of application problems that achieves either smaller networks or less error prone networ...

Full description

Saved in:
Bibliographic Details
Published inComputer (Long Beach, Calif.) Vol. 29; no. 3; pp. 45 - 54
Main Authors Yi Shang, Wah, B.W.
Format Journal Article
LanguageEnglish
Published New York IEEE 01.03.1996
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Algorithms
Feedforward neural networks
Feedforward systems
Heuristic algorithms
Minimization methods
Neural networks
Optimization
Optimization methods
Search methods
Supervised learning
Testing
Topology
Online AccessGet full text

Cover

More Information
Summary:We propose a novel global minimization method, called NOVEL (Nonlinear Optimization via External Lead), and demonstrate its superior performance on neural network learning problems. The goal is improved learning of application problems that achieves either smaller networks or less error prone networks of the same size. This training method combines global and local searches to find a good local minimum. In benchmark comparisons against the best global optimization algorithms, it demonstrates superior performance improvement.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0018-9162
1558-0814
DOI:10.1109/2.485892