Efficient distributed continual learning for steering experiments in real-time
Deep learning has emerged as a powerful method for extracting valuable information from
large volumes of data. However, when new training data arrives continuously (ie, is not fully …
large volumes of data. However, when new training data arrives continuously (ie, is not fully …
Noise-robust latent vector reconstruction in ptychography using deep generative models
Computational imaging is increasingly vital for a broad spectrum of applications, ranging
from biological to material sciences. This includes applications where the object is known …
from biological to material sciences. This includes applications where the object is known …
Accelerating time to science using CRADLE: a framework for materials data science
Modern materials science research problems present a challenge to data science and
analytics as experiments generate Petabyte-scale spatiotemporal datasets that span a …
analytics as experiments generate Petabyte-scale spatiotemporal datasets that span a …
Automated defect identification in coherent diffraction imaging with smart continual learning
X-ray Bragg coherent diffraction imaging is a powerful technique for 3D materials
characterization. However, obtaining X-ray diffraction data is difficult and computationally …
characterization. However, obtaining X-ray diffraction data is difficult and computationally …
Accelerated laminographic image reconstruction using GPUs
Laminography is a specialized 3D imaging technique optimized for examining flat,
elongated structures. Laminographic reconstruction is the process of generating 3D volume …
elongated structures. Laminographic reconstruction is the process of generating 3D volume …
Viper: A High-Performance I/O Framework for Transparently Updating, Storing, and Transferring Deep Neural Network Models
Scientific workflows increasingly need to train a DNN model in real-time during an
experiment (eg using ground truth from a simulation), while using it at the same time for …
experiment (eg using ground truth from a simulation), while using it at the same time for …
Diaspora: Resilience-Enabling Services for Real-Time Distributed Workflows
The need for real-time processing to enable automated decision making and experimental
steering has driven a shift from high-performance computing workflows on a centralized …
steering has driven a shift from high-performance computing workflows on a centralized …