1. Home
  2. Report Archives
  3. LDRD Annual Report FY2018
  4. High-Performance Computing, Simulation, and Data Science
  5. Strategic Initiative
  6. Large-Scale Multimodal Deep Learning for Nuclear Nonproliferation Analysis

Large-Scale Multimodal Deep Learning for Nuclear Nonproliferation Analysis

Barry Chen

Executive Summary

We are developing a deep-learning neural network system to discover and assess patterns in multimodal data gathered worldwide across all media fields for indicators of nuclear proliferation capabilities and activities, revolutionizing our data analytic capabilities to support national security, nonproliferation, cyber and space security, intelligence, and biosecurity.

Publications and Presentations

Chen, B. 2018. "Deep Learning: A Guide for Practitioners in the Physical Sciences." Phys. Plasmas. 25. doi: 10.1063/1.5020791. LLNL-JRNL-743970.

Cong, G. et al. 2018. "Accelerating Deep Neural Network Training for Action Recognition on a Cluster of GPUs." Supercomputing, Dallas, TX, Nov. 2018. LLNL-CONF-760618.

Feldman, Y., et al. 2018. "Toward a Multimodal-Deep Learning Retrieval System for Monitoring Nuclear Proliferation Activities." Journal of Nuclear Materials Management. LLNL-JRNL-751737.

Mundhenk, T. N., D. Ho, and B. Chen. 2018. "Improvements to Context Based Self-Supervised Learning." CVPR, Salt Lake City, UT, June 2018. LLNL-CONF-741553.