Application of Transfer Learning to Neutrino Interaction Classification

Abstract

Training deep neural networks using simulations typically requires very large numbers of simulated events. This can be a large computational burden and a limitation in the performance of the deep learning algorithm when insufficient numbers of events can be produced. We investigate the use of transfer learning, where a set of simulated images are used to fine tune a model trained on generic image recognition tasks, to the specific use case of neutrino interaction classification in a liquid argon time projection chamber. A ResNet18, pre-trained on photographic images, was fine-tuned using simulated neutrino images and when trained with one hundred thousand training events reached an F1 score of $0.896\pm 0.002$ compared to $0.836\pm 0.004$ from a randomly-initialised network trained with the same training sample. The transfer-learned networks also demonstrate lower bias as a function of energy and more balanced performance across different interaction types.

10 pages, 7 figures. Update to align with final published version, including commentary on network biases

References in corpus (5)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Neutrino interaction classification with a convolutional neural network in the DUNE far detector
• A Review on Machine Learning for Neutrino Experiments
• Climate impacts of particle physics

Cited by in corpus (6)

• A Method to Simultaneously Facilitate All Jet Physics Tasks
• Solving Key Challenges in Collider Physics with Foundation Models
• Interpretable Uncertainty Quantification in AI for HEP
• Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders
• Transfer Learning for Neutrino Scattering: Domain Adaptation with GANs
• LArTPC hit-based topology classification with quantum machine learning and symmetry