GMLS-Nets: A Machine Learning Framework for Unstructured Data by Nathaniel Trask
Nathaniel Trask (SNL), GMLS-Nets: A Machine Learning Framework for Unstructured Data
Data fields sampled on irregularly spaced points arise in many applications in the sciences and engineering. For regular grids, Convolutional Neural Networks (CNNs) have been successfully used to gain benefits from weight sharing and invariances. We generalize CNNs by introducing methods for data on unstructured point clouds based on Generalized Moving Least Squares (GMLS). GMLS is a non-parametric meshfree technique for estimating linear bounded functionals from scattered data, and has recently emerged as an effective technique for solving partial differential equations. By parameterizing the GMLS estimator, we obtain learning methods for linear and non-linear operators with unstructured stencils. In GMLS-Nets the necessary calculations are local, readily parallelizable, and the estimator is supported by a rigorous approximation theory. We show how the framework may be used for unstructured physical data sets to perform functional regression to identify associated differential operators, develop predictive dynamical models, and to obtain feature extractors to predict quantities of interest. The results show the promise of these architectures as foundations for data-driven model development in scientific machine learning applications.
Implementations in TensorFlow and PyTorch are available at
https://github.com/rgp62/gmls-nets
https://github.com/atzberg/gmls-nets
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)
Symposium papers: https://sites.google.com/view/aaai-mlps/proceedings
Slides: https://sites.google.com/view/aaai-mlps/program
Видео GMLS-Nets: A Machine Learning Framework for Unstructured Data by Nathaniel Trask канала MLPS - Combining AI and ML with Physics Sciences
Data fields sampled on irregularly spaced points arise in many applications in the sciences and engineering. For regular grids, Convolutional Neural Networks (CNNs) have been successfully used to gain benefits from weight sharing and invariances. We generalize CNNs by introducing methods for data on unstructured point clouds based on Generalized Moving Least Squares (GMLS). GMLS is a non-parametric meshfree technique for estimating linear bounded functionals from scattered data, and has recently emerged as an effective technique for solving partial differential equations. By parameterizing the GMLS estimator, we obtain learning methods for linear and non-linear operators with unstructured stencils. In GMLS-Nets the necessary calculations are local, readily parallelizable, and the estimator is supported by a rigorous approximation theory. We show how the framework may be used for unstructured physical data sets to perform functional regression to identify associated differential operators, develop predictive dynamical models, and to obtain feature extractors to predict quantities of interest. The results show the promise of these architectures as foundations for data-driven model development in scientific machine learning applications.
Implementations in TensorFlow and PyTorch are available at
https://github.com/rgp62/gmls-nets
https://github.com/atzberg/gmls-nets
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)
Symposium papers: https://sites.google.com/view/aaai-mlps/proceedings
Slides: https://sites.google.com/view/aaai-mlps/program
Видео GMLS-Nets: A Machine Learning Framework for Unstructured Data by Nathaniel Trask канала MLPS - Combining AI and ML with Physics Sciences
Показать
Комментарии отсутствуют
Информация о видео
30 марта 2020 г. 20:43:10
00:35:33
Другие видео канала
![Discovery of Physics and Characterization of Microstructure with Bayesian Hidden Physics Models](https://i.ytimg.com/vi/ObOS0C70iZc/default.jpg)
![Physics-Informed Machine Learning Simulator for Wildfire Propagation by Francesco Calisto](https://i.ytimg.com/vi/V2weFxU-Hyk/default.jpg)
![What is the difference between structured and unstructured data?](https://i.ytimg.com/vi/aQVDhxE1-sE/default.jpg)
![Deep learning for scientific computing: (closing) the gap between theory and practice by Ben Adcock](https://i.ytimg.com/vi/AElQ1huCNdU/default.jpg)
![Accelerating Simulation of Stiff Nonlinear Systems using Continuous-Time Echo State Nets, Rackauckas](https://i.ytimg.com/vi/3lM-Stc7z28/default.jpg)
![Using Structured & Unstructured Data together for Data Analytics](https://i.ytimg.com/vi/Japh7f_OWHM/default.jpg)
![Neural operator: A new paradigm for learning PDEs by Animashree Anandkumar](https://i.ytimg.com/vi/Lg2pgjDWqMM/default.jpg)
![But what is a neural network? | Chapter 1, Deep learning](https://i.ytimg.com/vi/aircAruvnKk/default.jpg)
![Introduction to PINNs](https://i.ytimg.com/vi/cFoe7SDcFPE/default.jpg)
![Neural Network Architectures & Deep Learning](https://i.ytimg.com/vi/oJNHXPs0XDk/default.jpg)
![EY Artificial Intelligence Innovation Center – Wavespace Madrid](https://i.ytimg.com/vi/mjJl8u3U2gM/default.jpg)
![Domain-Specific Entity Extraction from Unstructured Text - Zoran Dzunic and Mohamed AdelHady](https://i.ytimg.com/vi/wM6CWzv4VkQ/default.jpg)
![11. Introduction to Machine Learning](https://i.ytimg.com/vi/h0e2HAPTGF4/default.jpg)
![O'Reilly Webcast: MongoDB Schema Design: How to Think Non-Relational](https://i.ytimg.com/vi/PIWVFUtBV1Q/default.jpg)
![Accelerating high-fidelity combustion simulations with classification algorithms by Wai Tong Chung](https://i.ytimg.com/vi/nIMQm-aF968/default.jpg)
![What is Big Data | Big Data Types | Types of Data | Structured Data | Unstructured Data |](https://i.ytimg.com/vi/dK4aGzeBPkk/default.jpg)
![Targeted use of deep learning for physics-informed model discovery by Nathan Kutz](https://i.ytimg.com/vi/oS7NWbSe000/default.jpg)
![Neural ODEs for Data-Driven Reduced Order Modeling of Environmental Hydrodynamics by Sourav Dutta](https://i.ytimg.com/vi/U9F2zL-_Vk8/default.jpg)
![Document Classification and Unstructured Data Extraction SaaS Solution Offering for BPO and SI’s](https://i.ytimg.com/vi/tuxILQw08hc/default.jpg)
![Machine Learning Zero to Hero (Google I/O'19)](https://i.ytimg.com/vi/VwVg9jCtqaU/default.jpg)