A Fortran-Keras Deep Learning Bridge for Scientific Computing
Joint Authors
Ott, Jordan
Pritchard, Mike
Best, Natalie
Linstead, Erik
Curcic, Milan
Baldi, Pierre
Source
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-13, 13 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-08-28
Country of Publication
Egypt
No. of Pages
13
Main Subjects
Abstract EN
Implementing artificial neural networks is commonly achieved via high-level programming languages such as Python and easy-to-use deep learning libraries such as Keras.
These software libraries come preloaded with a variety of network architectures, provide autodifferentiation, and support GPUs for fast and efficient computation.
As a result, a deep learning practitioner will favor training a neural network model in Python, where these tools are readily available.
However, many large-scale scientific computation projects are written in Fortran, making it difficult to integrate with modern deep learning methods.
To alleviate this problem, we introduce a software library, the Fortran-Keras Bridge (FKB).
This two-way bridge connects environments where deep learning resources are plentiful with those where they are scarce.
The paper describes several unique features offered by FKB, such as customizable layers, loss functions, and network ensembles.
The paper concludes with a case study that applies FKB to address open questions about the robustness of an experimental approach to global climate simulation, in which subgrid physics are outsourced to deep neural network emulators.
In this context, FKB enables a hyperparameter search of one hundred plus candidate models of subgrid cloud and radiation physics, initially implemented in Keras, to be transferred and used in Fortran.
Such a process allows the model’s emergent behavior to be assessed, i.e., when fit imperfections are coupled to explicit planetary-scale fluid dynamics.
The results reveal a previously unrecognized strong relationship between offline validation error and online performance, in which the choice of the optimizer proves unexpectedly critical.
This in turn reveals many new neural network architectures that produce considerable improvements in climate model stability including some with reduced error, for an especially challenging training dataset.
American Psychological Association (APA)
Ott, Jordan& Pritchard, Mike& Best, Natalie& Linstead, Erik& Curcic, Milan& Baldi, Pierre. 2020. A Fortran-Keras Deep Learning Bridge for Scientific Computing. Scientific Programming،Vol. 2020, no. 2020, pp.1-13.
https://search.emarefa.net/detail/BIM-1209311
Modern Language Association (MLA)
Ott, Jordan…[et al.]. A Fortran-Keras Deep Learning Bridge for Scientific Computing. Scientific Programming No. 2020 (2020), pp.1-13.
https://search.emarefa.net/detail/BIM-1209311
American Medical Association (AMA)
Ott, Jordan& Pritchard, Mike& Best, Natalie& Linstead, Erik& Curcic, Milan& Baldi, Pierre. A Fortran-Keras Deep Learning Bridge for Scientific Computing. Scientific Programming. 2020. Vol. 2020, no. 2020, pp.1-13.
https://search.emarefa.net/detail/BIM-1209311
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1209311