Advances in Electron Microscopy with Deep Learning
This work provides a broad overview and several specific applications of deep learning to improve various aspects of electron microscopy for researchers in materials science and imaging.
This doctoral thesis explores the application of deep learning to electron microscopy, covering various aspects such as dataset creation, data analysis, learning rate stabilization, compressed sensing using GANs, adaptive sparse scanning with RNNs, signal-to-noise improvement, and exit wavefunction reconstruction with conditional GANs.
This doctoral thesis covers some of my advances in electron microscopy with deep learning. Highlights include a comprehensive review of deep learning in electron microscopy; large new electron microscopy datasets for machine learning, dataset search engines based on variational autoencoders, and automatic data clustering by t-distributed stochastic neighbour embedding; adaptive learning rate clipping to stabilize learning; generative adversarial networks for compressed sensing with spiral, uniformly spaced and other fixed sparse scan paths; recurrent neural networks trained to piecewise adapt sparse scan paths to specimens by reinforcement learning; improving signal-to-noise; and conditional generative adversarial networks for exit wavefunction reconstruction from single transmission electron micrographs. This thesis adds to my publications by presenting their relationships, reflections, and holistic conclusions. This version of my thesis is typeset for online dissemination to improve readability, whereas the thesis submitted to the University of Warwick in support of my application for the degree of Doctor of Philosophy in Physics is typeset for physical printing and binding.