X. G. Lu | Searcharxiv

arXiv2022

Vertex finding in neutrino-nucleus interaction: A Model Architecture Comparison

We compare different neural network architectures for Machine Learning (ML) algorithms designed to identify the neutrino interaction vertex position in the MINERvA detector. The architectures developed and optimized by hand are compared with the architectures developed in an automated way using the package "Multi-node Evolutionary Neural Networks for Deep Learning" (MENNDL), developed at Oak Ridge National Laboratory (ORNL). The two architectures resulted in a similar performance which suggests that the systematics associated with the optimized network architecture are small. Furthermore, we find that while the domain expert hand-tuned network was the best performer, the differences were negligible and the auto-generated networks performed well. There is always a trade-off between human, and computer resources for network optimization and this work suggests that automated optimization, assuming resources are available, provides a compelling way to save significant expert time.

hep-ex↗

arXiv2018

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

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.

physics.data-an↗