Levenberg-Marquardt and Conjugate Gradient methods applied to a high-order neural network

Chapter Title

Levenberg-Marquardt and Conjugate Gradient methods applied to a high-order neural network

Files

Department

Computer Science & Engineering Department

Description

The HONEST network is a high order neural network that uses product units and adaptable exponential weights. In this paper, we explore the use of several learning methods with the HONEST network: Levenberg-Marquardt (LM), Conjugate Gradient (CG), Scaled Conjugate Gradient (a technique that combines LM and CG), and resilient propagation (RP). Using a benchmark of 19 datasets, we find that the first three methods mentioned produce lower average test set errors than RP to a statistically significant extent. © 2013 IEEE.

Publication Date

12-1-2013

Document Type

Book Chapter

Book Title

Proceedings of the International Joint Conference on Neural Networks

ISBN

SCOPUS_ID:84893614990

Publisher

IEEE

City

Dallas, TX, USA

First Page

2123

Last Page

2129

Levenberg-Marquardt and Conjugate Gradient methods applied to a high-order neural network

Share

COinS