Nonlinear Knowledge-Based Classification
Abstract
Prior knowledge over general nonlinear sets is incorporated into nonlinear kernel classification
problems as linear constraints in a linear program. The key tool in this incorporation is a theorem
of the alternative for convex functions that converts nonlinear prior knowledge implications into
linear inequalities without the need to kernelize these implications. Effectiveness of the proposed
formulation is demonstrated on three publicly available classification datasets, including a cancer
prognosis dataset. Nonlinear kernel classifiers for these datasets exhibit marked improvements upon
the introduction of nonlinear prior knowledge compared to nonlinear kernel classifiers that do not
utilize such knowledge.
Subject
theorem of the alternative
linear programming
kernel classification
prior knowledge
Permanent Link
http://digital.library.wisc.edu/1793/64338Citation
06-04