18429

Deep learning: A guide for practitioners in the physical sciences

Brian K. Spears, James Brase, Peer-Timo Bremer, Barry Chen, John Field, Jim Gaffney, Michael Kruse, Steve Langer, Katie Lewis, Ryan Nora, Jayson Luc Peterson, Jayaraman Jayaraman Thiagarajan, Brian Van Essen, Kelli Humbird
Lawrence Livermore National Laboratory, Livermore, California 94551, USA
Physics of Plasmas, 25 (8), 080901, 2018

@article{spears2018deep,

   title={Deep learning: A guide for practitioners in the physical sciences},

   author={Spears, Brian K and Brase, James and Bremer, Peer-Timo and Chen, Barry and Field, John and Gaffney, Jim and Kruse, Michael and Langer, Steve and Lewis, Katie and Nora, Ryan and others},

   journal={Physics of Plasmas},

   volume={25},

   number={8},

   pages={080901},

   year={2018},

   publisher={AIP Publishing}

}

Download Download (PDF)   View View   Source Source   

717

views

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.
Rating: 2.0/5. From 1 vote.
Please wait...

Recent source codes

* * *

* * *

HGPU group © 2010-2018 hgpu.org

All rights belong to the respective authors

Contact us: