Deep learning: A guide for practitioners in the physical sciences

Abstract

Machine learning is finding increasingly broad application in the physical sciences.This most often involves building a model relationship between a dependent, measurable output and an associated set of controllable, but complicated, independent inputs. We present a tutorial on current techniques in machine learning ? a jumpingoff point for interested researchers to advance their work. We focus on deep neural networks with an emphasis on demystifying deep learning. We begin with background ideas in machine learning and some example applications from current research in plasma physics. We discuss supervised learning techniques for modeling complicated functions, beginning with familiar regression schemes, then advancing to more sophisticated deep learning methods. We also address unsupervised learning and techniques for reducing the dimensionality of input spaces. Along the way, we describe methods for practitioners to help ensure that their models generalize from their training data to as-yet-unseen test data. We describe classes of tasks -predicting scalars, handling images, fitting time-series -and prepare the reader to choose an appropriate technique. We finally point out some limitations to modern machine learning and speculate on some ways that practitioners from the physical sciences may be particularly suited to help. a) Electronic mail: spears9@llnl.gov 1 arXiv:1712.08523v1 [physics.comp-ph]

Inference of X-Ray Emission From a Plasma Focus Discharge: Comparison Between Characteristic Parameters and Neural Network Analyses

“…The parameters or signals that are processed by the machine learning algorithms need to be in a same value scale. The value range of ±1 is typically used [37], [38]. This is called the normalization process and it is detailed in Annex A.…”

“…The classification of the R values obtained better results and was more flexible to sort out the biased R values behaviour than a regression, i.e. to find a non linear function whose output is a predicted real value [39], although this latter alternative has more physical sense in this context [38]. Given the discussion above, the classification problem of the R values was considered in this work continuing the framework established in [34].…”

“…This diversity of signals poses the challenge of achieving good correlations results between the electrical signals and the photomultiplier X rays measurement. To complement the use of characteristic parameters that electrically describes the discharge for the correlations with other phenomena [24], [27], the use of machine learning algorithms, in particular the deep learning approach [36], has shown to be practical in the field of plasma diagnostics [37], [38]. Recently, it was used in plasma focus to infer the conditions for X rays emission based on only the signal from a Vivaldi antenna [34].…”

Building an open source software ecosystem for cross-disciplinary plasma research and education

“…The growth in size and complexity of data sets produced by plasma physics experiments, observations, and simulations highlights how critical openly available data science tools are to the infrastructure of plasma physics research. 16,17 Examples of data science tools which could be built within an open ecosystem include, but are not limited to: automated and reproducible feature detection and tracking in images (such as x-ray radiographs), rapid exploration of multi-dimensional parameter problems (as in designing inertial confinement fusion experiments), automated and reproducible processing of atomic spectra, big data processing using results from high repetition rate facilities, and searches for unexpected patterns in large data sets. Automation efforts would save scientists time from conducting repetitive tasks, and would enable real-time analysis of data during experimental campaigns.…”

“…Rice University 12) Atmospheric and Space Technologies Research Associates (ASTRA) LLC 13) SRI International 14) MIT Haystack Observatory 15) Space Sciences Laboratory, University of California Berkeley 16) Max Planck Institute for Plasma Physics 17) University of Southampton Software is crucial to all areas of modern plasma science research. Laboratory plasma physicists use software to interpret plasma diagnostics, analyze experimental results, and glean insights using advanced techniques from data science.…”