{"type":"ScholarlyArticle","title":"Avoiding Overfitting with BP-SOM","authors":[{"name":"Ton Weijters","slug":"ton-weijters","given":"Ton","family":"Weijters","affiliation":""},{"name":"H. Jaap van den Herik","slug":"h-jaap-van-den-herik","given":"H. Jaap","family":"van den Herik","affiliation":""},{"name":"Antal van den Bosch","slug":"antal-van-den-bosch","given":"Antal","family":"van den Bosch","affiliation":""},{"name":"Eric O. Postma","slug":"eric-o-postma","given":"Eric O.","family":"Postma","affiliation":""}],"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.","doi":null,"url":"https://ijcai.org/proceedings/1997/165","pdf":"https://ijcai.org/proceedings/1997/0165.pdf","markdown":"https://ijcai.org/proceedings/1997/165.md","bibtex":"https://ijcai.org/proceedings/1997/bibtex/165","volume":{"slug":"1997","title":"Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1997","url":"https://ijcai.org/proceedings/1997/","year":1997,"location":"Nagoya, Japan","dates":"","editors":"Martha E. Pollack","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Neural Networks","track":"Neural Networks","number":165,"pages":{"first":1140,"last":1144},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}