no code implementations • 30 Jan 2021 • Jordan Ott, David Bruyette, Cody Arbuckle, Dylan Balsz, Silke Hecht, Lisa Shubitz, Pierre Baldi
We also use the classification model to identify regions of interest and localize the disease in the radiographic images, as illustrated through visual heatmaps.
no code implementations • 11 Dec 2020 • Junze Liu, Jordan Ott, Julian Collado, Benjamin Jargowsky, Wenjie Wu, Jianming Bian, Pierre Baldi
To precisely reconstruct these kinematic characteristics of detected interactions at DUNE, we have developed and will present two CNN-based methods, 2-D and 3-D, for the reconstruction of final state particle direction and energy, as well as neutrino energy.
1 code implementation • 8 May 2020 • Lars Hertel, Julian Collado, Peter Sadowski, Jordan Ott, Pierre Baldi
Sherpa is a hyperparameter optimization library for machine learning models.
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.
1 code implementation • 17 Mar 2020 • Jordan Ott
Artificial Intelligence has historically relied on planning, heuristics, and handcrafted approaches designed by experts.
no code implementations • 3 Mar 2020 • Natalie Best, Jordan Ott, Erik Linstead
Transfer learning allows us to train deep architectures requiring a large number of learned parameters, even if the amount of available data is limited, by leveraging existing models previously trained for another task.
no code implementations • 21 Dec 2019 • Jordan Ott
Biology has clear constraints but by not using it as a guide we are constraining ourselves.
1 code implementation • 23 Sep 2019 • Jordan Ott, Erik Linstead, Nicholas LaHaye, Pierre Baldi
Weight-sharing is one of the pillars behind Convolutional Neural Networks and their successes.
4 code implementations • 3 Sep 2019 • Tom Beucler, Michael Pritchard, Stephan Rasp, Jordan Ott, Pierre Baldi, Pierre Gentine
Neural networks can emulate nonlinear physical systems with high accuracy, yet they may produce physically-inconsistent results when violating fundamental constraints.
Computational Physics Atmospheric and Oceanic Physics