Active learning with deep Bayesian neural network for laser control

Thomas C. Galvin; Sandrine I. Herriot; Brenda Ng; Wade H. Williams; Sachin S. Talathi; Thomas Spinka; Emily F. Sistrunk; Craig W. Siders; Constantin L. Haefner

doi:10.1117/12.2324364

7 September 2018 Active learning with deep Bayesian neural network for laser control

Thomas C. Galvin, Sandrine I. Herriot, Brenda Ng, Wade H. Williams, Sachin S. Talathi, Thomas Spinka, Emily F. Sistrunk, Craig W. Siders, Constantin L. Haefner

Author Affiliations +

Proceedings Volume 10751, Optics and Photonics for Information Processing XII; 107510N (2018) https://doi.org/10.1117/12.2324364
Event: SPIE Optical Engineering + Applications, 2018, San Diego, California, United States

Abstract

New control techniques are required to utilize the full potential of next generation high-energy high-repetition-rate pulses lasers while ensuring their safe operation. During automated optimization of an experiment, the control system is required to identify and reject unsafe laser configurations proposed by the optimizer. Using conventional physics codes render impossible when applied to a high energy laser system with 1ms or less time between shots, and also including laser fluctuations and drift. To mitigate this, we are using a deep Bayesian neural network to map the laser’s input power spectrum to its output power spectrum and demonstrate the speed of this approach. The Bayesian neural network can provide an estimate of its own uncertainty as a function of wavelength. A recently developed algorithm enables the uncertainty to be calculated inexpensively using multiple dropout layers inserted into the model. The uncertainty estimates are used by an active learning algorithm to improve the accuracy of the model and intelligently explore the input domain.

Citation Download Citation

Thomas C. Galvin, Sandrine I. Herriot, Brenda Ng, Wade H. Williams, Sachin S. Talathi, Thomas Spinka, Emily F. Sistrunk, Craig W. Siders, and Constantin L. Haefner "Active learning with deep Bayesian neural network for laser control", Proc. SPIE 10751, Optics and Photonics for Information Processing XII, 107510N (7 September 2018); https://doi.org/10.1117/12.2324364

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available