DMP3: a dynamic multilayer perceptron construction algorithm

This paper presents DMP3 (Dynamic Multilayer Perceptron 3), a multilayer perceptron (MLP) constructive training method that constructs MLPs by incrementally adding network elements of varying complexity to the network. DMP3 differs from other MLP construction techniques in several important ways, an...

Full description

Saved in:
Bibliographic Details
Published in:International journal of neural systems 2001-04, Vol.11 (2), p.145-165
Main Authors: Andersen, T L, Martinez, T R
Format: Article
Language:English
Subjects:
Algorithms
Neural Networks (Computer)
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents DMP3 (Dynamic Multilayer Perceptron 3), a multilayer perceptron (MLP) constructive training method that constructs MLPs by incrementally adding network elements of varying complexity to the network. DMP3 differs from other MLP construction techniques in several important ways, and the motivation for these differences are given. Information gain rather than error minimization is used to guide the growth of the network, which increases the utility of newly added network elements and decreases the likelihood that a premature dead end in the growth of the network will occur. The generalization performance of DMP3 is compared with that of several other well-known machine learning and neural network learning algorithms on nine real world data sets. Simulation results show that DMP3 performs better (on average) than any of the other algorithms on the data sets tested. The main reasons for this result are discussed in detail.
ISSN:0129-0657
DOI:10.1016/S0129-0657(01)00057-6