Studies of Stability and Robustness for Artificial Neural Networks and Boosted Decision Trees

Abstract

In this paper, we compare the performance, stability and robustness of Artificial Neural Networks (ANN) and Boosted Decision Trees (BDT) using MiniBooNE Monte Carlo samples. These methods attempt to classify events given a number of identification variables. The BDT algorithm has been discussed by us in previous publications. Testing is done in this paper by smearing and shifting the input variables of testing samples. Based on these studies, BDT has better particle identification performance than ANN. The degradation of the classifications obtained by shifting or smearing variables of testing results is smaller for BDT than for ANN.

23 pages, 13 figures

References in corpus (5)

• Evidence for Neutrino Oscillations from the Observation of Electron Anti-neutrinos in a Muon Anti-Neutrino Beam
• Boosted Decision Trees as an Alternative to Artificial Neural Networks for Particle Identification
• Studies of Boosted Decision Trees for MiniBooNE Particle Identification
• StatPatternRecognition: A C++ Package for Statistical Analysis of High Energy Physics Data
• Applying Rule Ensembles to the Search for Super-Symmetry at the Large Hadron Collider

Cited by in corpus (8)

• A Search for Electron Neutrino Appearance at the Delta m**2 ~ 1 eV**2 Scale
• Test of lepton universality in Upsilon(1S) decays at BaBar
• Application of artificial intelligence in the determination of impact parameter in heavy-ion collisions at intermediate energies
• QBDT, a new boosting decision tree method with systematic uncertainties into training for High Energy Physics
• Hadronic $b^{\prime }$ search at the LHC with top and W taggers
• Probing the Top Quark Flavour-Changing Neutral Current at a Future Electron-Positron Collider
• A Multivariate Training Technique with Event Reweighting
• Deep Neural Networks Guided Ensemble Learning for Point Estimation