Exploring order parameters and dynamic processes in disordered systems via variational autoencoders
نویسندگان
چکیده
We suggest and implement an approach for the bottom-up description of systems undergoing large-scale structural changes chemical transformations from dynamic atomically resolved imaging data, where only partial or uncertain data on atomic positions are available. This is predicated synergy two concepts, parsimony physical descriptors general rotational invariance non-crystalline solids, implemented using a rotationally-invariant extension variational autoencoder applied to semantically segmented atom-resolved seeking most effective reduced representation system that still contains maximum amount original information. allowed us explore evolution electron beam-induced processes in silicon-doped graphene system, but it can be also much broader range atomic-scale mesoscopic phenomena introduce order parameters their dynamics with time response external stimuli.
منابع مشابه
Linearizing Visual Processes with Convolutional Variational Autoencoders
This work studies the problem of modeling non-linear visual processes by learning linear generative models from observed sequences. We propose a joint learning framework, combining a Linear Dynamic System and a Variational Autoencoder with convolutional layers. After discussing several conditions for linearizing neural networks, we propose an architecture that allows Variational Autoencoders to...
متن کاملDiscrete Variational Autoencoders
Probabilistic models with discrete latent variables naturally capture datasets composed of discrete classes. However, they are difficult to train efficiently, since backpropagation through discrete variables is generally not possible. We introduce a novel class of probabilistic models, comprising an undirected discrete component and a directed hierarchical continuous component, that can be trai...
متن کاملInference Suboptimality in Variational Autoencoders
Amortized inference has led to efficient approximate inference for large datasets. The quality of posterior inference is largely determined by two factors: a) the ability of the variational distribution to model the true posterior and b) the capacity of the recognition network to generalize inference over all datapoints. We analyze approximate inference in variational autoencoders in terms of t...
متن کاملVariational Composite Autoencoders
Learning in the latent variable model is challenging in the presence of the complex data structure or the intractable latent variable. Previous variational autoencoders can be low effective due to the straightforward encoder-decoder structure. In this paper, we propose a variational composite autoencoder to sidestep this issue by amortizing on top of the hierarchical latent variable model. The ...
متن کاملSemi-Amortized Variational Autoencoders
Amortized variational inference (AVI) replaces instance-specific local inference with a global inference network. While AVI has enabled efficient training of deep generative models such as variational autoencoders (VAE), recent empirical work suggests that inference networks can produce suboptimal variational parameters. We propose a hybrid approach, to use AVI to initialize the variational par...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Science Advances
سال: 2021
ISSN: ['2375-2548']
DOI: https://doi.org/10.1126/sciadv.abd5084