Abstract
An event reweighting technique incorporated in multivariate training algorithms has been developed and tested with Artificial Neural Networks (ANN) and Boosted Decision Trees (BDT). The performance of the ANNs and BDTs resulting from this event reweighting training is compared to the performance from conventional equal event weighting training. The comparison is performed in the context of physics analysis in the ATLAS experiment at the Large Hadron Collider (LHC), which will explore the fundamental nature of matter and the basic forces that shape our universe. We demonstrate that the event reweighting technique provides an unbiased method of multivariate training for event pattern recognition.