Solving Inverse Problems with Deep Learning by Lexing Ying
Lexing Ying (Stanford), Solving Inverse Problems with Deep Learning.
http://web.stanford.edu/~lexing/
Abstract
This talk is about some recent progress on solving inverse problems using deep learning. Compared to traditional machine learning problems, inverse problems are often limited by the size of the training data set. We show how to overcome this issue by incorporating mathematical analysis and physics into the design of neural network architectures. We first describe neural network representations of pseudodifferential operators and Fourier integral operators. We then continue to discuss applications including electric impedance tomography, optical tomography, inverse acoustic/EM scattering, seismic imaging, and travel-time tomography.
AAAI 2020 Spring Symposium on Combining Artificial Intelligence and Machine Learning with Physics Sciences, March 23-25, 2020 (https://sites.google.com/view/aaai-mlps)
Papers: https://sites.google.com/view/aaai-mlps/proceedings
Slides: https://sites.google.com/view/aaai-mlps/program
Видео Solving Inverse Problems with Deep Learning by Lexing Ying канала MLPS - Combining AI and ML with Physics Sciences
http://web.stanford.edu/~lexing/
Abstract
This talk is about some recent progress on solving inverse problems using deep learning. Compared to traditional machine learning problems, inverse problems are often limited by the size of the training data set. We show how to overcome this issue by incorporating mathematical analysis and physics into the design of neural network architectures. We first describe neural network representations of pseudodifferential operators and Fourier integral operators. We then continue to discuss applications including electric impedance tomography, optical tomography, inverse acoustic/EM scattering, seismic imaging, and travel-time tomography.
AAAI 2020 Spring Symposium on Combining Artificial Intelligence and Machine Learning with Physics Sciences, March 23-25, 2020 (https://sites.google.com/view/aaai-mlps)
Papers: https://sites.google.com/view/aaai-mlps/proceedings
Slides: https://sites.google.com/view/aaai-mlps/program
Видео Solving Inverse Problems with Deep Learning by Lexing Ying канала MLPS - Combining AI and ML with Physics Sciences
Показать
Комментарии отсутствуют
Информация о видео
30 марта 2020 г. 20:43:13
00:45:26
Другие видео канала
![Bayesian Optimization and Machine Learning for Accelerating Experiments in the Physical Sciences](https://i.ytimg.com/vi/5n7UinKrMLk/default.jpg)
![On Human-robot Interactions via Multimodal Intent Modeling and Reachability-based Safety Assurance](https://i.ytimg.com/vi/4Rb1JcgPLCw/default.jpg)
![Nonlinear Model Reduction: Using ML to Enable Rapid Simulation of Extreme-Scale Physics Models](https://i.ytimg.com/vi/SJm-_nGV1Zk/default.jpg)
![Shanhui Fan -- Aspects of Nanophotonics Topology and Machine Learning](https://i.ytimg.com/vi/QD5D12mVJtw/default.jpg)
![MDS20 Minitutorial: Solving Inverse Problems with Deep Learning by Lexing Ying](https://i.ytimg.com/vi/826Wa7Pl1T0/default.jpg)
![The mother of all representer theorems for inverse problems & machine learning - Michael Unser](https://i.ytimg.com/vi/91M3SiSmLn0/default.jpg)
![International Zoom Inverse Problems Seminar, Jan 28, 2021, Lexing Ying (Stanford University)](https://i.ytimg.com/vi/Wh-wD24q45A/default.jpg)
![Learning to Solve Inverse Problems in Imaging - Willet - Workshop 1 - CEB T1 2019](https://i.ytimg.com/vi/ABH5KN5DTuc/default.jpg)
![Generalized Physics-Informed Learning through Language-Wide Differentiable Programming by Rackauckas](https://i.ytimg.com/vi/SEhMWkgcTOI/default.jpg)
![Maziar Raissi: "Hidden Physics Models: Machine Learning of Non-Linear Partial Differential Equat..."](https://i.ytimg.com/vi/GXZq2_WYRjo/default.jpg)
![Enforcing Constraints for Time Series Prediction in Supervised/Unsupervised/Reinforcement Learning](https://i.ytimg.com/vi/1kW6A51CJWs/default.jpg)
![Inverse Problems in Medical Imaging](https://i.ytimg.com/vi/9qQGIcF8rWQ/default.jpg)
![Chap 2: Hadamard & Picard Conditions, Singular Value Expansion, Naive Reconstruction - 1](https://i.ytimg.com/vi/XG0OBp-d7zI/default.jpg)
![Data-Driven Inverse Modeling with Incomplete Observations by Kailai Xu](https://i.ytimg.com/vi/0r9qekmZGqk/default.jpg)
![Samuli Siltanen: Reconstruction methods for ill-posed inverse problems - Part 1](https://i.ytimg.com/vi/PHgCwqqzj6Q/default.jpg)
![PhD Defence - Antoine Dupré](https://i.ytimg.com/vi/-0X21N4o1bM/default.jpg)
![GMLS-Nets: A Machine Learning Framework for Unstructured Data by Nathaniel Trask](https://i.ytimg.com/vi/bzjamKqPzOI/default.jpg)
![Joan Bruna "Learning Graph Inverse Problems with Neural Networks"](https://i.ytimg.com/vi/zuzO9JqeWN0/default.jpg)
![Lecture 13 - Debugging ML Models and Error Analysis | Stanford CS229: Machine Learning (Autumn 2018)](https://i.ytimg.com/vi/ORrStCArmP4/default.jpg)
![Understanding and Mitigating Gradient Flow Pathologies in PINN by Paris Perdikaris](https://i.ytimg.com/vi/OFUkRgCI6No/default.jpg)