no code implementations • 21 Feb 2021 • Massimiliano Lupo Pasini, Vittorio Gabbi, Junqi Yin, Simona Perotto, Nouamane Laanait
We propose a distributed approach to train deep convolutional generative adversarial neural network (DC-CGANs) models.
no code implementations • 24 Sep 2019 • Nouamane Laanait, Joshua Romero, Junqi Yin, M. Todd Young, Sean Treichler, Vitalii Starchenko, Albina Borisevich, Alex Sergeev, Michael Matheson
We introduce novel communication strategies in synchronous distributed Deep Learning consisting of decentralized gradient reduction orchestration and computational graph-aware grouping of gradient tensors.
no code implementations • NeurIPS Workshop Deep_Invers 2019 • Nouamane Laanait, Junqi Yin, Albina Borisevich
The phase problem in diffraction physics is one of the oldest inverse problems in all of science.
1 code implementation • 22 Mar 2019 • Suhas Somnath, Chris R. Smith, Nouamane Laanait, Rama K. Vasudevan, Anton Ievlev, Alex Belianinov, Andrew R. Lupini, Mallikarjun Shankar, Sergei V. Kalinin, Stephen Jesse
The second is Pycroscopy, which provides algorithms for scientific analysis of nanoscale imaging and spectroscopy modalities and is built on top of pyUSID and USID.
Data Analysis, Statistics and Probability
no code implementations • 19 Feb 2019 • Nouamane Laanait, Qian He, Albina Y. Borisevich
Deep learning has demonstrated superb efficacy in processing imaging data, yet its suitability in solving challenging inverse problems in scientific imaging has not been fully explored.