Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment

Abstract

We present a simulation-based study using deep convolutional neural networks (DCNNs) to identify neutrino interaction vertices in the MINERvA passive targets region, and illustrate the application of domain adversarial neural networks (DANNs) in this context. DANNs are designed to be trained in one domain (simulated data) but tested in a second domain (physics data) and utilize unlabeled data from the second domain so that during training only features which are unable to discriminate between the domains are promoted. MINERvA is a neutrino-nucleus scattering experiment using the NuMI beamline at Fermilab. $A$-dependent cross sections are an important part of the physics program, and these measurements require vertex finding in complicated events. To illustrate the impact of the DANN we used a modified set of simulation in place of physics data during the training of the DANN and then used the label of the modified simulation during the evaluation of the DANN. We find that deep learning based methods offer significant advantages over our prior track-based reconstruction for the task of vertex finding, and that DANNs are able to improve the performance of deep networks by leveraging available unlabeled data and by mitigating network performance degradation rooted in biases in the physics models used for training.

41 pages

References in corpus (8)

• The GENIE Neutrino Monte Carlo Generator
• Deep Learning and its Application to LHC Physics
• The NuMI Neutrino Beam
• A Convolutional Neural Network Neutrino Event Classifier
• Design, Calibration, and Performance of the MINERvA Detector
• Neutrino Flux Predictions for the NuMI Beam
• Measurement of Ratios of ${\nu }_{\mu }$ Charged-Current Cross Sections on C, Fe, and Pb to CH at Neutrino Energies 2-20 GeV
• Measurement of Partonic Nuclear Effects in Deep-Inelastic Neutrino Scattering using MINERvA

Cited by in corpus (14)

• A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• Applications and Techniques for Fast Machine Learning in Science
• Improved Energy Reconstruction in NOvA with Regression Convolutional Neural Networks
• A Convolutional Neural Network for Multiple Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• Context-Enriched Identification of Particles with a Convolutional Network for Neutrino Events
• A Review on Machine Learning for Neutrino Experiments
• Pulse shape discrimination using a convolutional neural network for organic liquid scintillator signals
• Neural Network predictions of inclusive electron-nucleus cross sections
• Accelerating Machine Learning Inference with GPUs in ProtoDUNE Data Processing
• How to set up your first machine learning project in astronomy
• Adversarial methods to reduce simulation bias in neutrino interaction event filtering at Liquid Argon Time Projection Chambers
• Contrastive Learning for Robust Representations of Neutrino Data
• Neutral pion reconstruction using machine learning in the MINERvA experiment at $⟨E_{\nu }⟩\sim 6$ GeV
• Vertex finding in neutrino-nucleus interaction: A Model Architecture Comparison