Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
On the Use of Neural Network Ensembles in QSAR and QSPR Dimitris K. Agrafiotis,* Walter Ceden~o, and Victor S. Lobanov
 

Summary: On the Use of Neural Network Ensembles in QSAR and QSPR
Dimitris K. Agrafiotis,* Walter Ceden~o, and Victor S. Lobanov
3-Dimensional Pharmaceuticals, Inc., 665 Stockton Drive, Exton, Pennsylvania 19341
Received March 26, 2002
Despite their growing popularity among neural network practitioners, ensemble methods have not been
widely adopted in structure-activity and structure-property correlation. Neural networks are inherently
unstable, in that small changes in the training set and/or training parameters can lead to large changes in
their generalization performance. Recent research has shown that by capitalizing on the diversity of the
individual models, ensemble techniques can minimize uncertainty and produce more stable and accurate
predictors. In this work, we present a critical assessment of the most common ensemble technique known
as bootstrap aggregation, or bagging, as applied to QSAR and QSPR. Although aggregation does offer
definitive advantages, we demonstrate that bagging may not be the best possible choice and that simpler
techniques such as retraining with the full sample can often produce superior results. These findings are
rationalized using Krogh and Vedelsby's decomposition of the generalization error into a term that measures
the average generalization performance of the individual networks and a term that measures the diversity
among them. For networks that are designed to resist over-fitting, the benefits of aggregation are clear but
not overwhelming.
I. INTRODUCTION
Artificial neural networks are rapidly becoming the method
of choice for structure-activity and structure-property

  

Source: Agrafiotis, Dimitris K. - Molecular Design and Informatics Group, Johnson & Johnson Pharmaceutical Research and Development

 

Collections: Chemistry; Computer Technologies and Information Sciences