Combine and conquer: event reconstruction with Bayesian Ensemble Neural Networks

Araz, Jack Y.; Spannowsky, Michael

Abstract

Ensemble learning is a technique where multiple component learners are combined through a protocol. We propose an Ensemble Neural Network (ENN) that uses the combined latent-feature space of multiple neural network classifiers to improve the representation of the network hypothesis. We apply this approach to construct an ENN from Convolutional and Recurrent Neural Networks to discriminate top-quark jets from QCD jets. Such ENN provides the flexibility to improve the classification beyond simple prediction combining methods by linking different sources of error correlations, hence improving the representation between data and hypothesis. In combination with Bayesian techniques, we show that it can reduce epistemic uncertainties and the entropy of the hypothesis by simultaneously exploiting various kinematic correlations of the system, which also makes the network less susceptible to a limitation in training sample size.

Citation

Araz, J. Y., & Spannowsky, M. (2021). Combine and conquer: event reconstruction with Bayesian Ensemble Neural Networks. Journal of High Energy Physics, 2021(4), Article 296. https://doi.org/10.1007/jhep04%282021%29296

• Journal Article Type: Article
• Acceptance Date: Apr 2, 2021
• Online Publication Date: Apr 30, 2021
• Publication Date: 2021
• Deposit Date: Jul 28, 2021
• Publicly Available Date: Aug 23, 2021
• Journal: Journal of High Energy Physics
• Print ISSN: 1126-6708
• Electronic ISSN: 1029-8479
• Publisher: Scuola Internazionale Superiore di Studi Avanzati (SISSA)
• Peer Reviewed: Peer Reviewed
• Volume: 2021
• Issue: 4
• Article Number: 296
• DOI: https://doi.org/10.1007/jhep04%282021%29296
• Public URL: https://durham-repository.worktribe.com/output/1244882