Logo image
Modifying the generalisation characteristics of a neural network with interactive reinforcement training
Conference paper   Open access

Modifying the generalisation characteristics of a neural network with interactive reinforcement training

K.W. Wong, C.C. Fung and H. Eren
1997 IEEE International Conference on Intelligent Processing Systems (Cat. No.97TH8335), Vol.1, pp.472-476
IEEE
Proceedings of the 1997 IEEE International Conference on Intelligent Processing Systems, ICIPS'97 (Beijing, China, 28/10/1998–31/10/1998)
1998
pdf
modifying_the_generalisation_characteristics.pdfDownloadView
Published (Version of Record) Open Access
url
Link to Published Version *Subscription may be requiredView

Abstract

An interactive reinforcement training approach to modify the generalisation characteristics of a backpropagation neural network is proposed. The objective is to ensure that the network is capable of recognising significant training data even they are low in number. The interactive process will reinforce the important data by duplicating them. It ensures that the significant data are included in the final network. A case study of porosity prediction in petroleum exploration is used to illustrate this approach. Results have shown that the network's generalisation ability is modified to include the important outliners while avoiding overfitting. It is also useful in cases where training data are difficult or expensive to obtain.

Details

Metrics

200 File views/ downloads
66 Record Views
Logo image