Fast training of multilayer perceptrons with a mixed norm algorithm

A new fast training algorithm for the multilayer perceptron (MLP) is proposed. This new algorithm is based on the optimization of a mixed least square (LS) and a least fourth (LF) criterion producing a modified form of the standard back propagation algorithm (SBP). To determine the updating rules in...

Full description

Saved in:
Bibliographic Details
Main Authors: Abid, S., Fnaiech, F., Jervis, B.W., Cheriet, M.
Format: Conference Proceeding
Language:English
Subjects:
Artificial intelligence
Back
Backpropagation algorithms
Biomedical imaging
Convergence
Laboratories
Least squares approximation
Least squares methods
Multilayer perceptrons
Neurons
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A new fast training algorithm for the multilayer perceptron (MLP) is proposed. This new algorithm is based on the optimization of a mixed least square (LS) and a least fourth (LF) criterion producing a modified form of the standard back propagation algorithm (SBP). To determine the updating rules in the hidden layers, an analogous back propagation strategy used in the conventional learning algorithms is developed. This permits the application of the learning procedure to all the layers. Experimental results on benchmark applications and a real medical problem are obtained which indicates significant reduction in the total number of iterations, the convergence time, and the generalization capacity when compared to those of the SBP algorithm.
ISSN:2161-4393
2161-4407
DOI:10.1109/IJCNN.2005.1555992