Partial Scanning Transmission Electron Microscopy with Deep Learning

@article{Ede2020PartialST,
  title={Partial Scanning Transmission Electron Microscopy with Deep Learning},
  author={Jeffrey M. Ede and Richard Beanland},
  journal={Scientific Reports},
  year={2020},
  volume={10}
}
Compressed sensing algorithms are used to decrease electron microscope scan time and electron beam exposure with minimal information loss. Following successful applications of deep learning to compressed sensing, we have developed a two-stage multiscale generative adversarial neural network to complete realistic 512 × 512 scanning transmission electron micrographs from spiral, jittered gridlike, and other partial scans. For spiral scans and mean squared error based pre-training, this enables… 
Advances in Electron Microscopy with Deep Learning
TLDR
This doctoral thesis covers some of the advances in electron microscopy with deep learning and adds to the publications by presenting their relationships, reflections, and holistic conclusions.
Adaptive Partial Scanning Transmission Electron Microscopy with Reinforcement Learning
  • Jeffrey M. Ede
  • Computer Science, Engineering
    Machine Learning: Science and Technology
  • 2021
TLDR
This work has extended recurrent deterministic policy gradients to train deep LSTMs and differentiable neural computers to adaptively sample scan path segments and shows that this approach outperforms established algorithms based on spiral scans.
Advances in Electron Microscopy with Deep Learning
TLDR
Thesis Structure, Connections, and Partial Scanning Transmission Electron Microscopy with Deep Learning: A Review of the Building Blocks of Deep Learning.
Deep learning for the classification of medical kidney disease: a pilot study for electron microscopy
TLDR
Good overall classification is found with the MedKidneyEM-v1 Classifier and when looking at normal and diseased kidneys, the average area under the curve for precision and recall was 0.841, which demonstrates the feasibility of deep learning for electron microscopy.
Deep learning in electron microscopy
  • Jeffrey M. Ede
  • Computer Science, Physics
    Mach. Learn. Sci. Technol.
  • 2021
TLDR
This review paper offers a practical perspective aimed at developers with limited familiarity of deep learning in electron microscopy that discusses hardware and software needed to get started with deep learning and interface with electron microscopes.
Defect Detection in Atomic Resolution Transmission Electron Microscopy Images Using Machine Learning
TLDR
Two self-supervised machine learning algorithms that are trained solely on images that are defect-free are proposed that use principal components analysis (PCA) and convolutional neural networks (CNN) to analyze a TEM image and predict the location of a defect.
Enabling autonomous scanning probe microscopy imaging of single molecules with deep learning.
TLDR
An algorithm that controlled the operation of an Atomic Force Microscope (AFM) that, without the need of user intervention, allowed acquiring multiple high-resolution images of different molecules and brings SPM a step closer to full autonomous operation.
Five-second STEM dislocation tomography for 300 nm thick specimen assisted by deep-learning-based noise filtering
TLDR
A deep-learning-assisted rapid STEM tomography is demonstrated, which visualizes 3D dislocation arrangement only within five-second acquisition of all the tilt-series images even in a 300 nm thick steel specimen and offers a new platform for various in situ or operando 3D microanalyses in which dealing with relatively thick specimens or covering media like liquid cells are required.
Making the most of your electrons: Challenges and opportunities in characterizing hybrid interfaces with STEM
TLDR
A review of recent developments in the field and additional experimental investigations and simulations are supplemented to present solutions for attaining a nano or molecular-level understanding of these interfaces of hybrid composites.
Recent Advances and Applications of Deep Learning Methods in Materials Science
Deep learning (DL) is one of the fastest growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities. DL allows
...
1
2
...

References

SHOWING 1-10 OF 111 REFERENCES
Rectifier Nonlinearities Improve Neural Network Acoustic Models
TLDR
This work explores the use of deep rectifier networks as acoustic models for the 300 hour Switchboard conversational speech recognition task, and analyzes hidden layer representations to quantify differences in how ReL units encode inputs as compared to sigmoidal units.
Neural networks for machine learning lecture 6a overview of mini-batch gradient descent
  • Cited on, p. 14, 2012.
  • 2012
On robust estimation of the location parameter
Theoretical framework of statistical noise in scanning transmission electron microscopy.
TLDR
It is found that normalizing annular-bright-field image by total electron count in the bright field significantly suppress the noise, and it is shown that ptychography is the most efficient imaging for weak phase objects.
Radiation damage in the TEM and SEM.
TLDR
In the light of recent experimental evidence, two common assumptions are re-examine: that the amount of radiation damage is proportional to the electron dose and is independent of beam diameter; and that the extent of the damage is proportionate to theamount of energy deposited in the specimen.
A Survey on Data Collection for Machine Learning: A Big Data - AI Integration Perspective
TLDR
This survey performs a comprehensive study of data collection from a data management point of view, providing a research landscape of these operations, guidelines on which technique to use when, and identify interesting research challenges.
Adversarial Signal Denoising with Encoder-Decoder Networks
TLDR
This work introduces an encoder-decoder architecture to denoise signals, represented by a sequence of measurements, and proposes an adversarial learning formulation where the goal is to align the clean and noisy signal latent representation given that both signals pass through the encoder.
AutoML: A Survey of the State-of-the-Art
TLDR
A comprehensive and up-to-date review of the state-of-the-art (SOTA) in AutoML methods according to the pipeline, covering data preparation, feature engineering, hyperparameter optimization, and neural architecture search (NAS).
MGGAN: Solving Mode Collapse Using Manifold-Guided Training
TLDR
A new algorithm, namely, the manifold-guided generative adversarial network (MGGAN), which leverages a guidance network on existing GAN architecture to induce the generator to learn the overall modes of a data distribution and is an effective and efficient tool for improving the diversity of GANs.
Acknowledgements Thanks go to Julie Robinson for advice on finding publication venues and to Marin Alexe for helpful discussion
  • http://www.inkscape.org/
  • 2020
...
1
2
3
4
5
...