zoom link https://lbnl.zoom.us/j/97341258188
Abstract: The last decade’s revolution in machine learning has spilled over from industry to find increasingly broad applications in fundamental sciences. Across the DOE, the wealth of data, robust automation, and requirements for control, simulation, and data acquisition, make “Big Science” experiments — telescopes, particle accelerators, etc. — ideal targets for machine learning. In this talk I will describe SLAC’s approach to machine learning applications across the science mission, I will highlight several examples in autonomous optimization of accelerators, analysis and acquisition of x-ray free-electron laser data, and single-particle imaging with cryo-EM.
Speaker Bio: Daniel Ratner began his scientific career at NYC’s MoMA using x-ray and optical methods to support art conservation. He then earned his Ph.D. in accelerator physics at Stanford under Alex Chao and John Galayda, working on topics including the commissioning of LCLS and steady-state microbunching for EUV generation. Since then he has developed various projects including microbunched coherent electron cooling, electron and pump-probe ghost imaging, a demonstration of soft x-ray self-seeding, and several machine learning applications for accelerators. He is currently leading SLAC's new lab-wide machine learning initiative