Search Results for author:
Found 12 papers, 11 papers with code
Deep learning at the edge enables real-time streaming ptychographic imaging
Coherent microscopy techniques provide an unparalleled multi-scale view of materials across scientific and technological fields, from structural materials to quantum devices, from integrated circuits to biological cells.
Masked Sinogram Model with Transformer for ill-Posed Computed Tomography Reconstruction: a Preliminary Study
Inspired by the success of transformer for natural language processing, the core idea of this preliminary study is to consider a projection of tomography as a word token, and the whole scan of the cross-section (A. K. A.
FAIR principles for AI models with a practical application for accelerated high energy diffraction microscopy
A concise and measurable set of FAIR (Findable, Accessible, Interoperable and Reusable) principles for scientific data is transforming the state-of-practice for data management and stewardship, supporting and enabling discovery and innovation.
fairDMS: Rapid Model Training by Data and Model Reuse
Extracting actionable information rapidly from data produced by instruments such as the Linac Coherent Light Source (LCLS-II) and Advanced Photon Source Upgrade (APS-U) is becoming ever more challenging due to high (up to TB/s) data rates.
BFTrainer: Low-Cost Training of Neural Networks on Unfillable Supercomputer Nodes
We describe how the task of rescaling suitable DNN training tasks to fit dynamically changing holes can be formulated as a deterministic mixed integer linear programming (MILP)-based resource allocation algorithm, and show that this MILP problem can be solved efficiently at run time.
Bridging Data Center AI Systems with Edge Computing for Actionable Information Retrieval
Extremely high data rates at modern synchrotron and X-ray free-electron laser light source beamlines motivate the use of machine learning methods for data reduction, feature detection, and other purposes.
Fast and accurate learned multiresolution dynamical downscaling for precipitation
We compare the four new CNN-derived high-resolution precipitation results with precipitation generated from original high resolution simulations, a bilinear interpolater and the state-of-the-art CNN-based super-resolution (SR) technique.
Joint ptycho-tomography with deep generative priors
In our simulations, we demonstrate that our proposed framework with parameter tuning and learned priors generates high-quality reconstructions under limited and noisy measurement data.
BraggNN: Fast X-ray Bragg Peak Analysis Using Deep Learning
When applied to a real experimental dataset, a 3D reconstruction that used peak positions computed by BraggNN yields 15% better results on average as compared to a reconstruction obtained using peak positions determined using conventional 2D pseudo-Voigt fitting.
Scientific Image Restoration Anywhere
We explore this question by evaluating the performance and accuracy of a scientific image restoration model, for which both model input and output are images, on edge computing devices.
Deep Learning Accelerated Light Source Experiments
Experimental protocols at synchrotron light sources typically process and validate data only after an experiment has completed, which can lead to undetected errors and cannot enable online steering.
TomoGAN: Low-Dose Synchrotron X-Ray Tomography with Generative Adversarial Networks
We present \TOMOGAN{}, a denoising technique based on generative adversarial networks, for improving the quality of reconstructed images for low-dose imaging conditions.
