Physics-based Deep Learning
- URL: http://arxiv.org/abs/2109.05237v1
- Date: Sat, 11 Sep 2021 09:38:02 GMT
- Title: Physics-based Deep Learning
- Authors: Nils Thuerey and Philipp Holl and Maximilian Mueller and Patrick
Schnell and Felix Trost and Kiwon Um
- Abstract summary: Digital book contains a practical and comprehensive introduction to everything related to deep learning in the context of physical simulations.
Includes hands-on code examples in the form of Jupyter notebooks to quickly get started.
Beyond standard supervised learning from data, we'll look at physical loss constraints, more tightly coupled learning algorithms with differentiable simulations, as well as reinforcement learning and uncertainty modeling.
- Score: 22.248409468073145
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This digital book contains a practical and comprehensive introduction of
everything related to deep learning in the context of physical simulations. As
much as possible, all topics come with hands-on code examples in the form of
Jupyter notebooks to quickly get started. Beyond standard supervised learning
from data, we'll look at physical loss constraints, more tightly coupled
learning algorithms with differentiable simulations, as well as reinforcement
learning and uncertainty modeling. We live in exciting times: these methods
have a huge potential to fundamentally change what computer simulations can
achieve.
Related papers
- A Physics-embedded Deep Learning Framework for Cloth Simulation [6.8806198396336935]
This paper proposes a physics-embedded learning framework that directly encodes physical features of cloth simulation.
The framework can also integrate with other external forces and collision handling through either traditional simulators or sub neural networks.
arXiv Detail & Related papers (2024-03-19T15:21:00Z) - Hindsight States: Blending Sim and Real Task Elements for Efficient
Reinforcement Learning [61.3506230781327]
In robotics, one approach to generate training data builds on simulations based on dynamics models derived from first principles.
Here, we leverage the imbalance in complexity of the dynamics to learn more sample-efficiently.
We validate our method on several challenging simulated tasks and demonstrate that it improves learning both alone and when combined with an existing hindsight algorithm.
arXiv Detail & Related papers (2023-03-03T21:55:04Z) - Deep Learning and Computational Physics (Lecture Notes) [0.5156484100374059]
Notes should be accessible to a typical engineering graduate student with a strong background in Applied Mathematics.
Use concepts from computational physics to develop an understanding of deep learning algorithms.
Several novel deep learning algorithms can be used to solve challenging problems in computational physics.
arXiv Detail & Related papers (2023-01-03T03:56:19Z) - Continual learning autoencoder training for a particle-in-cell
simulation via streaming [52.77024349608834]
upcoming exascale era will provide a new generation of physics simulations with high resolution.
These simulations will have a high resolution, which will impact the training of machine learning models since storing a high amount of simulation data on disk is nearly impossible.
This work presents an approach that trains a neural network concurrently to a running simulation without data on a disk.
arXiv Detail & Related papers (2022-11-09T09:55:14Z) - Continual Predictive Learning from Videos [100.27176974654559]
We study a new continual learning problem in the context of video prediction.
We propose the continual predictive learning (CPL) approach, which learns a mixture world model via predictive experience replay.
We construct two new benchmarks based on RoboNet and KTH, in which different tasks correspond to different physical robotic environments or human actions.
arXiv Detail & Related papers (2022-04-12T08:32:26Z) - Emulating Quantum Dynamics with Neural Networks via Knowledge
Distillation [8.741611658931337]
High-fidelity quantum dynamics emulators can be used to predict the time evolution of complex physical systems.
We introduce an efficient training framework for constructing machine learning-based emulators.
arXiv Detail & Related papers (2022-03-19T00:21:39Z) - Evaluating Continual Learning Algorithms by Generating 3D Virtual
Environments [66.83839051693695]
Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment.
We propose to leverage recent advances in 3D virtual environments in order to approach the automatic generation of potentially life-long dynamic scenes with photo-realistic appearance.
A novel element of this paper is that scenes are described in a parametric way, thus allowing the user to fully control the visual complexity of the input stream the agent perceives.
arXiv Detail & Related papers (2021-09-16T10:37:21Z) - Data-Efficient Learning for Complex and Real-Time Physical Problem
Solving using Augmented Simulation [49.631034790080406]
We present a task for navigating a marble to the center of a circular maze.
We present a model that learns to move a marble in the complex environment within minutes of interacting with the real system.
arXiv Detail & Related papers (2020-11-14T02:03:08Z) - Fast Modeling and Understanding Fluid Dynamics Systems with
Encoder-Decoder Networks [0.0]
We show that an accurate deep-learning-based proxy model can be taught efficiently by a finite-volume-based simulator.
Compared to traditional simulation, the proposed deep learning approach enables much faster forward computation.
We quantify the sensitivity of the deep learning model to key physical parameters and hence demonstrate that the inversion problems can be solved with great acceleration.
arXiv Detail & Related papers (2020-06-09T17:14:08Z) - Learning to Simulate Complex Physics with Graph Networks [68.43901833812448]
We present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains.
Our framework---which we term "Graph Network-based Simulators" (GNS)--represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing.
Our results show that our model can generalize from single-timestep predictions with thousands of particles during training, to different initial conditions, thousands of timesteps, and at least an order of magnitude more particles at test time.
arXiv Detail & Related papers (2020-02-21T16:44:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.