Application of Neural Networks to b - quark jet detection in Z →

A multilayer perceptron (MLP) artificial neural network (NN) was trained with Monte Carlo data to detect b-jets. A variety of NNs were tested to maximize performance. The best NN was run on data with different reconstruction options. It was found that a simple MLP NN with 6 variables and 6 hidden neurons performed better than using only a decay length significance cut for detecting b-jets. The NN was run on data from the DØ experiment to measure the mass of the Z boson from Z → bb̄ decays. Simple background subtraction techniques were used to yield a shifted Z peak at 73.3± 3.4 GeV.