Deep learning for electron microscopy

December 28, 2018, US Department of Energy
The same image shown using different analysis methods. a) Raw electron microscopy image. b) Defects (white) as labelled by a human expert. c) Defects (white) as labelled by a Fourier transform method. d) Defects (white) as labelled by the optimal neural network. Defects that don’t exist are shown in purple, and defects that weren’t identified are orange. In mere hours, researchers created a neural network that performed as well as a human expert, demonstrating MENNDL’s ability to significantly reduce the time to analyze electron microscopy images. Credit: US Department of Energy

Finding defects in electron microscopy images takes months. Now, there's a faster way. It's called MENNDL, the Multinode Evolutionary Neural Networks for Deep Learning. It creates artificial neural networks—computational systems that loosely mimic the human brain—that tease defects out of dynamic data. It runs on all available nodes of the Summit supercomputer, performing 152 thousand million million calculations a second.

In mere hours, scientists using MENNDL created a that performed as well as a human expert. It reduces the time to analyze electron microscopy images by months. MENNDL is the first known approach to automatically identify atomic-level structural information in scanning transmission electron microscopy data. In 2018, MENNDL received an R&D 100 award, considered the Oscars of innovation. It's also a finalist for the Gordon Bell award.

MENNDL, an artificial intelligence system, automatically designed an optimal network to extract structural information from raw atomic-resolution microscopy data. To design the network, MENNDL used 18,000 GPUs on all of the available 3000 nodes of the Summit supercomputer. In a few hours, MENNDL creates and evaluates millions of networks using a scalable, parallel, asynchronous genetic algorithm augmented with a support vector machine to automatically find a superior deep learning network topology and hyper-parameter set. This work is far faster than could be done by a human expert. For the application of electron microscopy, the system furthers the goal of better understanding the electron-beam-matter interactions and real-time image-based feedback, which enables a huge step beyond human capacity toward nanofabricating materials automatically.

Explore further: Researchers use Titan to accelerate design, training of deep learning networks

More information: 167-PFlops deep learning for electron microscopy: From learning physics to atomic manipulation. SC'18: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, Dallas, TX (2018).

Related Stories

Team breaks exaop barrier with deep learning application

October 9, 2018

A team of computational scientists from Lawrence Berkeley National Laboratory (Berkeley Lab) and Oak Ridge National Laboratory (ORNL) and engineers from NVIDIA has, for the first time, demonstrated an exascale-class deep ...

Predicting the accuracy of a neural network prior to training

December 14, 2018

Constructing a neural network model for each new dataset is the ultimate nightmare for every data scientist. What if you could forecast the accuracy of the neural network earlier thanks to accumulated experience and approximation? ...

Recommended for you

What happened before the Big Bang?

March 26, 2019

A team of scientists has proposed a powerful new test for inflation, the theory that the universe dramatically expanded in size in a fleeting fraction of a second right after the Big Bang. Their goal is to give insight into ...

Cellular microRNA detection with miRacles

March 26, 2019

MicroRNAs (miRNAs) are short noncoding regulatory RNAs that can repress gene expression post-transcriptionally and are therefore increasingly used as biomarkers of disease. Detecting miRNAs can be arduous and expensive as ...

Race at the edge of the sun: Ions are faster than atoms

March 26, 2019

Scientists at the University of Göttingen, the Institut d'Astrophysique in Paris and the Istituto Ricerche Solari Locarno have observed that ions move faster than atoms in the gas streams of a solar prominence. The results ...

Physicists discover new class of pentaquarks

March 26, 2019

Tomasz Skwarnicki, professor of physics in the College of Arts and Sciences at Syracuse University, has uncovered new information about a class of particles called pentaquarks. His findings could lead to a new understanding ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.