37 citations · 38 across the 3 of their papers we have counts for
3 papers
cs.LG2023
Addressing Discontinuous Root-Finding for Subsequent Differentiability in Machine Learning, Inverse Problems, and Control
Daniel Johnson, Ronald Fedkiw
There are many physical processes that have inherent discontinuities in their mathematical formulations. This paper is motivated by the specific case of collisions between two rigi…
cs.LG2023★ 1 cited
Software-based Automatic Differentiation is Flawed
Daniel Johnson, Trevor Maxfield, Yongxu Jin +1
Various software efforts embrace the idea that object oriented programming enables a convenient implementation of the chain rule, facilitating so-called automatic differentiation v…
physics.comp-ph2019★ 37 cited
Coercing Machine Learning to Output Physically Accurate Results
Zhenglin Geng, Dan Johnson, Ronald Fedkiw
Many machine/deep learning artificial neural networks are trained to simply be interpolation functions that map input variables to output values interpolated from the training data…