Kevin Carlberg - AI for Computational Physics: Toward real-time high-fidelity simulation

Автор: Physics Informed Machine Learning

Загружено: 2021-04-09

Просмотров: 5586

Описание:

Talk starts at 1:30

Dr. Kevin Carlberg speaking in the UW Data-driven methods in science and engineering seminar on April 9, 2021.

For more information including past and upcoming talks, visit: http://www.databookuw.com/seminars/

Sign up for notifications of future talks: https://mailman11.u.washington.edu/ma...

Abstract: The explosion of artificial intelligence—especially techniques arising from deep neural networks—has yielded exciting advances in fields such as computer vision, natural language processing, and reinforcement learning. However, the application of these methods to problems in engineering and science remains limited. In this talk, we describe how two particular recent advances in deep learning, namely convolutional autoencoders and long-short-term-memory (LSTM) recurrent neural networks (RNNs) can be employed to overcome two longstanding challenges in nonlinear model reduction: the Kolmogorov limitation of linear subspaces, and accurate error quantification.

Kevin Carlberg - AI for Computational Physics: Toward real-time high-fidelity simulation

Доступные форматы для скачивания:

Скачать видео mp4

Информация по загрузке:

Скачать аудио mp3

Похожие видео

Nicholas Zabaras - Physics Informed Learning for Multiscale Dynamical Systems

Nicholas Zabaras - Physics Informed Learning for Multiscale Dynamical Systems

ИИ для физики и физика для ИИ

ИИ для физики и физика для ИИ

George Karniadakis - From PINNs to DeepOnets

George Karniadakis - From PINNs to DeepOnets

DDPS | ML for Solving PDEs: Neural Operators on Function Spaces by Anima Anandkumar

DDPS | ML for Solving PDEs: Neural Operators on Function Spaces by Anima Anandkumar

Почему «Трансформеры» заменяют CNN?

Почему «Трансформеры» заменяют CNN?

Designing Next-Generation Numerical Methods with Physics-Informed Neural Networks

Designing Next-Generation Numerical Methods with Physics-Informed Neural Networks

Самая сложная модель из тех, что мы реально понимаем

Самая сложная модель из тех, что мы реально понимаем

Почему нельзя строить как раньше?

Почему нельзя строить как раньше?

Anima Anandkumar - Neural operator: A new paradigm for learning PDEs

Anima Anandkumar - Neural operator: A new paradigm for learning PDEs

Liquid Neural Networks

Liquid Neural Networks

The Code That Revolutionized Orbital Simulation

The Code That Revolutionized Orbital Simulation

Physics Informed Machine Learning: High Level Overview of AI and ML in Science and Engineering

Physics Informed Machine Learning: High Level Overview of AI and ML in Science and Engineering

One in a Billion Moments in Nature

One in a Billion Moments in Nature

Scientific Machine Learning: Where Physics-based Modeling Meets Data-driven Learning

Scientific Machine Learning: Where Physics-based Modeling Meets Data-driven Learning

Interpretable Deep Learning for New Physics Discovery

Interpretable Deep Learning for New Physics Discovery

Rethinking Physics Informed Neural Networks [NeurIPS'21]

Rethinking Physics Informed Neural Networks [NeurIPS'21]

Andrew Stuart - Supervised Learning For Operators

Andrew Stuart - Supervised Learning For Operators

Machine Learning for Computational Fluid Dynamics

Machine Learning for Computational Fluid Dynamics

The Strange Math That Predicts (Almost) Anything

The Strange Math That Predicts (Almost) Anything

Моделирование Монте-Карло

Моделирование Монте-Карло