Lawrence Livermore National Laboratory



Back to top

Back to top

Texas A&M’s Department of Nuclear Engineering honored Livermore physicist Kelli Humbird with its 2020–21 Young Former Student award for her work combining machine learning with inertial confinement fusion (ICF) research at the Laboratory. Humbird graduated from Texas A&M with a Ph.D. in nuclear engineering in 2019. Since joining Livermore as an intern in 2016, she has made key contributions to the ICF program such as creating a widely used neural network algorithm—DJINN (Deep Jointly Informed Neural Networks)—to help produce higher performing implosions and applying a technique called “transfer learning” to create a more predictive model of ICF experiments.

A paper co-authored by Livermore computer scientist Rushil Anirudh received the Best Paper Honorable Mention award at the 2021 IEEE Winter Conference on Applications of Computer Vision. In “Generative Patch Priors for Practical Compressive Image Recovery,” Anirudh and co-authors from Mitsubishi Electric Research Laboratories and Arizona State University demonstrated a new type of prior that can outperform common techniques in compressive sensing and compressive phase retrieval tasks. The authors determined that generative patch priors are more broadly applicable to a wide variety of images than competitors, and they proposed a technique enabling the model to automatically calibrate itself against real world sensor distortions and corruptions.