Related papers: Which priors matter? Benchmarking models for learning latent dynamics

Which priors matter? Benchmarking models for learning latent dynamics

URL: http://arxiv.org/abs/2111.05458v1
Date: Tue, 9 Nov 2021 23:48:21 GMT
Title: Which priors matter? Benchmarking models for learning latent dynamics
Authors: Aleksandar Botev and Andrew Jaegle and Peter Wirnsberger and Daniel Hennes and Irina Higgins
Abstract summary: Several methods have proposed to integrate priors from classical mechanics into machine learning models. We take a sober look at the current capabilities of these models. We find that the use of continuous and time-reversible dynamics benefits models of all classes.
Score: 70.88999063639146
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Learning dynamics is at the heart of many important applications of machine learning (ML), such as robotics and autonomous driving. In these settings, ML algorithms typically need to reason about a physical system using high dimensional observations, such as images, without access to the underlying state. Recently, several methods have proposed to integrate priors from classical mechanics into ML models to address the challenge of physical reasoning from images. In this work, we take a sober look at the current capabilities of these models. To this end, we introduce a suite consisting of 17 datasets with visual observations based on physical systems exhibiting a wide range of dynamics. We conduct a thorough and detailed comparison of the major classes of physically inspired methods alongside several strong baselines. While models that incorporate physical priors can often learn latent spaces with desirable properties, our results demonstrate that these methods fail to significantly improve upon standard techniques. Nonetheless, we find that the use of continuous and time-reversible dynamics benefits models of all classes.

Related papers

Learning System Dynamics without Forgetting [60.08612207170659]
Predicting trajectories of systems with unknown dynamics is crucial in various research fields, including physics and biology. We present a novel framework of Mode-switching Graph ODE (MS-GODE), which can continually learn varying dynamics. We construct a novel benchmark of biological dynamic systems, featuring diverse systems with disparate dynamics.
arXiv Detail & Related papers (2024-06-30T14:55:18Z)
Towards a population-informed approach to the definition of data-driven models for structural dynamics [0.0]
A population-based scheme is followed here and two different machine-learning algorithms from the meta-learning domain are used. The algorithms seem to perform as intended and outperform a traditional machine-learning algorithm at approximating the quantities of interest.
arXiv Detail & Related papers (2023-07-19T09:45:41Z)
Learning continuous models for continuous physics [94.42705784823997]
We develop a test based on numerical analysis theory to validate machine learning models for science and engineering applications. Our results illustrate how principled numerical analysis methods can be coupled with existing ML training/testing methodologies to validate models for science and engineering applications.
arXiv Detail & Related papers (2022-02-17T07:56:46Z)
Constructing Neural Network-Based Models for Simulating Dynamical Systems [59.0861954179401]
Data-driven modeling is an alternative paradigm that seeks to learn an approximation of the dynamics of a system using observations of the true system. This paper provides a survey of the different ways to construct models of dynamical systems using neural networks. In addition to the basic overview, we review the related literature and outline the most significant challenges from numerical simulations that this modeling paradigm must overcome.
arXiv Detail & Related papers (2021-11-02T10:51:42Z)
Physics-Guided Deep Learning for Dynamical Systems: A survey [5.733401663293044]
Traditional physics-based models are interpretable but rely on rigid assumptions. Deep learning provides novel alternatives for efficiently recognizing complex patterns and emulating nonlinear dynamics. It aims to take the best from both physics-based modeling and state-of-the-art DL models to better solve scientific problems.
arXiv Detail & Related papers (2021-07-02T20:59:03Z)
GEM: Group Enhanced Model for Learning Dynamical Control Systems [78.56159072162103]
We build effective dynamical models that are amenable to sample-based learning. We show that learning the dynamics on a Lie algebra vector space is more effective than learning a direct state transition model. This work sheds light on a connection between learning of dynamics and Lie group properties, which opens doors for new research directions.
arXiv Detail & Related papers (2021-04-07T01:08:18Z)
Model-Based Deep Learning [155.063817656602]
Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques. Deep neural networks (DNNs) use generic architectures which learn to operate from data, and demonstrate excellent performance. We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches.
arXiv Detail & Related papers (2020-12-15T16:29:49Z)
Modeling System Dynamics with Physics-Informed Neural Networks Based on Lagrangian Mechanics [3.214927790437842]
Two main modeling approaches often fail to meet requirements: first principles methods suffer from high bias, whereas data-driven modeling tends to have high variance. We present physics-informed neural ordinary differential equations (PINODE), a hybrid model that combines the two modeling techniques to overcome the aforementioned problems. Our findings are of interest for model-based control and system identification of mechanical systems.
arXiv Detail & Related papers (2020-05-29T15:10:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.