Search NASA⌕ Search

Engineering topics

Krishnapriyan, Aditi

Publications and source records attributed to Krishnapriyan, Aditi.

Characterizing possible failure modes in physics-informed neural networks (characterizing-pinns-failure-modes) v0.1.0

This software provides an implementation of the physics-informed neural network setup for different differential equations. It provides a way to solve differential equations using machine learning, via a physical constraint term in the loss function. Physics-informed neural networks are a popular approach, but here, the failures of such an approach are characterized and better solutions and training procedures are provided.

Krishnapriyan, Aditi↗

molecule-tda v0.1.0

A general framework to extract topological information (via topological data analysis) from some type of point cloud data, to be used in downstream machine learning tasks.

Krishnapriyan, Aditi↗

2016 T Division Lightning Talks

These are the slides for all of the 2016 T Division lightning talks. There are 350 pages worth of slides from different presentations, all of which cover different topics within the theoretical division at Los Alamos National Laboratory (LANL).

99 GENERAL AND MISCELLANEOUS↗