Avoiding Overfitting with BP-SOM
Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence. Neural Networks. Pages 1140-1144.
Abstract
Overfitting is a well-known problem in the fields of symbolic and connectionist machine l ea rning. It describes the deterioration of generalisation performance of a trained model. In this paper , we investigate the ability of a novel artificial neural network , BP -S OM , to avoid overfitting. BP-SOM is a hybrid neural network which combines a multi-layered feed-forwa rd network (MFN) with Kohon en 's self-organising maps (soMs). During training, supervised back-propagation learning and unsupervised SOM learning cooperate in finding adequate hidden-layer representations . We show that BP-SOM outperforms standard backpropagation, and also back-propagation with a weight decay when dealing with the problem of overfitting. In addition, we show that BP-SOM succeeds in preserving generalisation performance under hidden-unit pruning , where both other m et hods fail.
@inproceedings{ijcai1997p165,
title = {Avoiding Overfitting with BP-SOM},
author = {Weijters, Ton and van den Herik, H. Jaap and van den Bosch, Antal and Postma, Eric O.},
booktitle = {Proceedings of the Fifteenth International Joint Conference on
Artificial Intelligence, {IJCAI-97}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Martha E. Pollack},
pages = {1140--1144},
year = {1997},
note = {Neural Networks},
url = {https://ijcai.org/proceedings/1997/165},
}
TY - CPAPER TI - Avoiding Overfitting with BP-SOM AU - Weijters, Ton AU - van den Herik, H. Jaap AU - van den Bosch, Antal AU - Postma, Eric O. T2 - Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, IJCAI-97 PB - International Joint Conferences on Artificial Intelligence PY - 1997 SP - 1140 EP - 1144 UR - https://ijcai.org/proceedings/1997/165 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
