Change search
ReferencesLink to record
Permanent link

Direct link
Random brains
Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
2013 (English)In: The 2013 International Joint Conference on Neural Networks (IJCNN): Proceedings, IEEE conference proceedings, 2013, 1-8 p.Conference paper (Refereed)
Abstract [en]

In this paper, we introduce and evaluate a novel method, called random brains, for producing neural network ensembles. The suggested method, which is heavily inspired by the random forest technique, produces diversity implicitly by using bootstrap training and randomized architectures. More specifically, for each base classifier multilayer perceptron, a number of randomly selected links between the input layer and the hidden layer are removed prior to training, thus resulting in potentially weaker but more diverse base classifiers. The experimental results on 20 UCI data sets show that random brains obtained significantly higher accuracy and AUC, compared to standard bagging of similar neural networks not utilizing randomized architectures. The analysis shows that the main reason for the increased ensemble performance is the ability to produce effective diversity, as indicated by the increase in the difficulty diversity measure.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2013. 1-8 p.
National Category
Information Systems
Research subject
Computer and Systems Sciences
URN: urn:nbn:se:su:diva-100718DOI: 10.1109/IJCNN.2013.6707026ISBN: 978-1-4673-6128-6OAI: diva2:695728
The 2013 International Joint Conference on Neural Networks (IJCNN), Dallas, Texas, USA, 4-9 August 2013
Available from: 2014-02-12 Created: 2014-02-12 Last updated: 2014-02-19Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Boström, Henrik
By organisation
Department of Computer and Systems Sciences
Information Systems

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 136 hits
ReferencesLink to record
Permanent link

Direct link