10-14 October 2016
San Francisco Marriott Marquis
America/Los_Angeles timezone

Deep-Learning Analysis Pipelines on Raw HEP Data from the Daya Bay Neutrino Experiment at NERSC

10 Oct 2016, 12:00
Sierra A (San Francisco Mariott Marquis)

Sierra A

San Francisco Mariott Marquis

Oral Track 5: Software Development Track 5: Software Development


Samuel Kohn (Lawrence Berkeley National Lab. (US))


The use of up-to-date machine learning methods, including deep neural networks, running directly on raw data has significant potential in High Energy Physics for revealing patterns in detector signals and as a result improving reconstruction and the sensitivity of the final physics analyses. In this work, we describe a machine-learning analysis pipeline developed and operating at the National Energy Research Scientific Computing Center (NERSC), processing data from the Daya Bay Neutrino Experiment. We apply convolutional neural networks to raw data from Daya Bay in an unsupervised mode where no input physics knowledge or training labels are used.

Primary Keyword (Mandatory) Artificial intelligence/Machine learning
Tertiary Keyword (Optional) High performance computing
Secondary Keyword (Optional) Analysis tools and techniques

Primary author

Mr Evan Racah (Lawrence Berkeley National Lab. (US))


Craig Tull (LBNL/ATLAS) Dan Dwyer (Lawrence Berkeley National Lab) Lisa Gerhardt (LBNL) Mr Prabhat (Lawrence Berkeley National Lab. (US)) Peter Sadowski (University of California Irvine) Samuel Kohn (Lawrence Berkeley National Lab. (US)) Thorsten Kurth (Lawrence Berkeley National Lab. (US)) Wahid Bhimji (Lawrence Berkeley National Lab. (US))

Presentation Materials