Robust training of multilayer perceptrons: some experimental results

Andrew J. Myles; Alan F. Murray; Andrew M. Wallace

doi:10.1117/12.205094

6 April 1995 Robust training of multilayer perceptrons: some experimental results

Andrew J. Myles, Alan F. Murray, Andrew M. Wallace

Proceedings Volume 2492, Applications and Science of Artificial Neural Networks; (1995) https://doi.org/10.1117/12.205094
Event: SPIE's 1995 Symposium on OE/Aerospace Sensing and Dual Use Photonics, 1995, Orlando, FL, United States

Abstract

Robust regression methods are a useful alternative to least squares for modelling real data sets, which generally contain outliers. Various authors have previously examined the use of these methods for modelling such data using multilayer perceptrons (MLPs), with impressive results. This paper describes some experimental experiences with the use of some simple robust methods for MLP training. The use of robust error measures for testing is demonstrated, and the use of more than one robust error for testing MLPs during the training process is recommended. The failure of one simple robust training method due to leverage points is demonstrated, and preliminary results from a method which may assist in the identification of these points are provided. Finally, the problem of overfitting when using robust methods is discussed briefly.

Citation Download Citation

Andrew J. Myles, Alan F. Murray, and Andrew M. Wallace "Robust training of multilayer perceptrons: some experimental results", Proc. SPIE 2492, Applications and Science of Artificial Neural Networks, (6 April 1995); https://doi.org/10.1117/12.205094

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available