Variational Autoencoder Inverse Mapper: An End-to-End Deep Learning Framework for Inverse Problems
Journal
Proceedings of the International Joint Conference on Neural Networks
Journal Volume
2021-July
Date Issued
2021
Author(s)
Abstract
Inverse problems - using measured observations to determine unknown parameters - are well motivated but challenging in many science and engineering problems. In this paper, we propose an end-to-end deep learning framework, the Variational Autoencoder Inverse Mapper (VAIM), as an autoencoder-based neural network architecture for inverse problems. The encoder and decoder neural networks approximate the forward and backward mapping, respectively, and a variational latent layer is incorporated into VAIM to learn the posterior parameter distributions with respect to given observables. We demonstrate the effectiveness of VAIM for several toy inverse problems, with both finite and infinite solutions, and for constructing the inverse function mapping quantum correlation functions to observables in a Quantum Chromodynamics analysis of nucleon structure. ? 2021 IEEE.
Subjects
end-to-end learning
ill-posed
inverse problems
latent space analysis
variational autoencoder
Deep learning
Inverse problems
Mapping
Multilayer neural networks
Network architecture
Quantum theory
Auto encoders
End to end
End-to-end learning
Engineering problems
Ill posed
Latent space analyse
Learning frameworks
Science and engineering
Space analysis
Variational autoencoder
Differential equations
Type
conference paper