Data modelling with neural networks: Advantages and limitations |
| |
| Authors: | D.J. Livingstone D.T. Manallack I.V. Tetko |
| |
| Affiliation: | (1) Centre for Molecular Design, University of Portsmouth, Halpern House, 1-2 Hampshire Terrace, Portsmouth, PO1 2QF, U.K.;(2) Chiroscience Ltd., Cambridge Science Park, Milton Road, Cambridge, CB4 4WE, U.K.;(3) Institute of Bioorganic and Petroleum Chemistry, Ukrainian Academy of Sciences, Murmanskaya 1, Kiev-660, 253660, Ukraine |
| |
| Abstract: | The origins and operation of artificial neural networks are briefly described and their early application to data modelling in drug design is reviewed. Four problems in the use of neural networks in data modelling are discussed, namely overfitting, chance effects, overtraining and interpretation, and examples are given of the means by which the first three of these may be avoided. The use of neural networks as a variable selection tool is shown and the advantage of networks as a nonlinear data modelling device is discussed. The display of multivariate data in two dimensions employing a neural network is illustrated using experimental and theoretical data for a set of charge transfer complexes. |
| |
| Keywords: | Overfitting Overtraining Data display Chance effects Nonlinear relationships Variable selection |
| 本文献已被 SpringerLink 等数据库收录！ |
|
