MLExchange: A web-based platform enabling exchangeable machine learning workflows for scientific studies

no code implementations • 20 Aug 2022 • Zhuowen Zhao, Tanny Chavez, Elizabeth A. Holman, Guanhua Hao, Adam Green, Harinarayan Krishnan, Dylan McReynolds, Ronald Pandolfi, Eric J. Roberts, Petrus H. Zwart, Howard Yanxon, Nicholas Schwarz, Subramanian Sankaranarayanan, Sergei V. Kalinin, Apurva Mehta, Stuart Campbell, Alexander Hexemer

Machine learning (ML) algorithms are showing a growing trend in helping the scientific communities across different disciplines and institutions to address large and diverse data problems.

AutoPhaseNN: Unsupervised Physics-aware Deep Learning of 3D Nanoscale Bragg Coherent Diffraction Imaging

1 code implementation • 28 Sep 2021 • YuDong Yao, Henry Chan, Subramanian Sankaranarayanan, Prasanna Balaprakash, Ross J. Harder, Mathew J. Cherukara

The problem of phase retrieval, or the algorithmic recovery of lost phase information from measured intensity alone, underlies various imaging methods from astronomy to nanoscale imaging.

Astronomy Retrieval

Real-time 3D Nanoscale Coherent Imaging via Physics-aware Deep Learning

no code implementations • 16 Jun 2020 • Henry Chan, Youssef S. G. Nashed, Saugat Kandel, Stephan Hruszkewycz, Subramanian Sankaranarayanan, Ross J. Harder, Mathew J. Cherukara

Phase retrieval, the problem of recovering lost phase information from measured intensity alone, is an inverse problem that is widely faced in various imaging modalities ranging from astronomy to nanoscale imaging.

Astronomy Retrieval

Combinatorial Black-Box Optimization with Expert Advice

no code implementations • 6 Jun 2020 • Hamid Dadkhahi, Karthikeyan Shanmugam, Jesus Rios, Payel Das, Samuel Hoffman, Troy David Loeffler, Subramanian Sankaranarayanan

We consider the problem of black-box function optimization over the boolean hypercube.