A Fortran-Keras Deep Learning Bridge for Scientific Computing

2 code implementations • 14 Apr 2020 • Jordan Ott, Mike Pritchard, Natalie Best, Erik Linstead, Milan Curcic, Pierre Baldi

Implementing artificial neural networks is commonly achieved via high-level programming languages like Python and easy-to-use deep learning libraries like Keras.

Revised Estimates of Ocean Surface Drag in Strong Winds

1 code implementation • 24 Feb 2020 • Milan Curcic, Brian K. Haus

The drag coefficient saturates at $2. 6 \times 10^{-3}$ and $U_{10} \approx 25\ m\ s^{-1}$, in agreement with previous laboratory results.

Atmospheric and Oceanic Physics Fluid Dynamics

A parallel Fortran framework for neural networks and deep learning

6 code implementations • 18 Feb 2019 • Milan Curcic

Ease of use and computational performance are similar to an existing popular machine learning framework, making neural-fortran a viable candidate for further development and use in production.