Deep learning: A guide for practitioners in the physical sciences

Machine learning is finding increasingly broad applications 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...

Full description

Saved in:
Bibliographic Details
Published in:Physics of plasmas 2018-08, Vol.25 (8)
Main Authors: Spears, Brian K., Brase, James, Bremer, Peer-Timo, Chen, Barry, Field, John, Gaffney, Jim, Kruse, Michael, Langer, Steve, Lewis, Katie, Nora, Ryan, Peterson, Jayson Luc, Jayaraman Thiagarajan, Jayaraman, Van Essen, Brian, Humbird, Kelli
Format: Article
Language:English
Subjects:
70 PLASMA PHYSICS AND FUSION TECHNOLOGY
Artificial intelligence
Artificial neural networks
Deep learning
Lasers
Machine learning
Mathematics and Computing
Neural networks
Physical sciences
Physics
Plasma physics
Scalars
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine learning is finding increasingly broad applications 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 jumping-off 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, and 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, and 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.
ISSN:1070-664X
1089-7674
DOI:10.1063/1.5020791