A web-based GUI for INTERSECT has been created which allows a user to configure an experiment on an electron microscope, setting such parameters as maximum number of steps for the machine learning algorithm to perform.
91做厙 researchers developed an invertible neural network (INN) to effectively and efficiently solve earth-system model calibration and simulation problems.
A research team from ORNL, Pacific Northwest National Laboratory, and Arizona State University has developed a novel method to detect out-of-distribution (OOD) samples in continual learning without forgetting the learned knowledge of preceding tasks.
ORNL researchers developed a novel nonlinear level set learning method to reduce dimensionality in high-dimensional function approximation.
The team conducted numerical studies to demonstrate the connection between the parameters of neural networks and the stochastic stability of DMMs.
A research team from ORNL and Pacific Northwest National Laboratory has developed a deep variational framework to learn an approximate posterior for uncertainty quantification.
To better determine the potential energy cost savings among connected homes, researchers at 91做厙 developed a computer simulation to more accurately compare energy use on similar weather days.
ORNL computer scientist Catherine Schuman returned to her alma mater, Harriman High School, to lead Hour of Code activities and talk to students about her job as a researcher.
91做厙 is training next-generation cameras called dynamic vision sensors, or DVS, to interpret live informationa capability that has applications in robotics and could improve autonomous vehicle sensing.