- Scientific Computing and Data Management
- Machine Learning and Data Classification
- Advanced X-ray Imaging Techniques
- Distributed and Parallel Computing Systems
- Research Data Management Practices
- Computer Graphics and Visualization Techniques
- Advanced Data Storage Technologies
SLAC National Accelerator Laboratory
2022
Stanford University
2021
Extremely high data rates at modern synchrotron and X-ray free-electron laser light source beamlines motivate the use of machine learning methods for reduction, feature detection, other purposes. Regardless application, basic concept is same: collected in early stages an experiment, from past similar experiments, and/or simulated upcoming experiment are used to train models that, effect, learn specific characteristics those data; these then process subsequent more efficiently than would...
We present a case for low batch-size inference with the potential adaptive training of lean encoder model. do so in context paradigmatic example machine learning as applied data acquisition at high velocity scientific user facilities such Linac Coherent Light Source-II x-ray Free-Electron Laser. discuss how low-latency model operating edge can capitalize on naturally stochastic nature sources. simulate method attosecond angular streaking to produce representative results whereby simulated...
Extremely high data rates at modern synchrotron and X-ray free-electron laser light source beamlines motivate the use of machine learning methods for reduction, feature detection, other purposes. Regardless application, basic concept is same: collected in early stages an experiment, from past similar experiments, and/or simulated upcoming experiment are used to train models that, effect, learn specific characteristics those data; these then process subsequent more efficiently than would...
The emergence of novel computational hardware is enabling a new paradigm for rapid machine learning model training. For the Department Energy’s major research facilities, this developing technology will enable highly adaptive approach to experimental sciences. In manuscript we present per-epoch and end-to-end training times an example streaming diagnostic that planned upcoming high-repetition rate x-ray Free Electron Laser, Linac Coherent Light Source-II. We explore parameter space batch...