Publication details

Branch & Bound algorithm with partial prediction for use with recursive and non-recursive criterion forms

Conference Paper (international conference)

Somol Petr, Pudil Pavel, Grim Jiří

serial: Advances in Pattern Recognition - ICAPR 2001. Proceedings, p. 425-434 , Eds: Singh S., Murshed N., Kropatsch W.

publisher: Springer, (Heidelberg 2001)


action: ICAPR /2./, (Rio de Janeiro, BR, 11.03.2001-14.03.2001)

research: AV0Z1075907

project(s): VS96063, GA MŠk, ME 187, GA MŠk, KSK1075601, GA AV ČR

keywords: branch and bound, search tree, optimal subset selection

preview: Download

abstract (eng):

We introduce a novel algorithm for optimal feature selection. As opposed to our recent Fast Branch & Bound (FBB) algorithm the new algorithm is well suitable for use with recursive criterion forms. Even if the new algorithm does not operate as effectively as the FBB algorithm, it is able to find the optimum significantly faster than any other Branch & Bound.

Cosati: 09K, 09J