Multiclass cascades for ensemble-based boosting algorithms

Teo Susnjak*, Andre Barczak, Napoleon Reyes, Ken Hawick

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

2 Citations (Scopus)
24 Downloads (Pure)


We propose a general method applicable to existing multiclass boosting-algorithms for creating cascaded classifiers. The motivation is to introduce more tractability to machine learning tasks which require large datasets and involve complex decision boundaries, by way of separate-and-conquer strategies that reduce both the training and detection-phase overheads. The preliminary study explored the application of our method to AdaBoost.ECC on six UCI datasets and found that a decrease in the computational training and evaluation overheads occurred without significant effects on the generalization of the classifiers.

Original languageEnglish
Title of host publicationSTAIRS 2012: Proceedings of the Sixth Starting AI Researchers' Symposium
EditorsK. Kersting, M. Toussaint
PublisherIOS Press
Number of pages6
ISBN (Electronic)978-1-61499-096-3
ISBN (Print)9781614990956
Publication statusPublished - 2012
Externally publishedYes

Publication series

NameFrontiers in Artificial Intelligence and Applications
ISSN (Print)0922-6389


Dive into the research topics of 'Multiclass cascades for ensemble-based boosting algorithms'. Together they form a unique fingerprint.

Cite this