Learning Dynamics of Spring-Mass Models with Physics-Informed Graph Neural Networks

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Isogeometric analysis (IGA) was introduced to integrate methods for analysis and computer-aided design (CAD) into a unified process. High-quality parameterization of a physical domain plays a crucial role in IGA. However, obtaining high-quality parameteriz ...

Neural-network quantum states (NQS) have been shown to be a suitable variational ansatz to simulate out-of-equilibrium dynamics in two-dimensional systems using timedependent variational Monte Carlo (t-VMC). In particular, stable and accurate time propagat ...

Non-convex constrained optimization problems have become a powerful framework for modeling a wide range of machine learning problems, with applications in k-means clustering, large- scale semidefinite programs (SDPs), and various other tasks. As the perfor ...

With the onset of large-scale astronomical surveys capturing millions of images, there is an increasing need to develop fast and accurate deconvolution algorithms that generalize well to different images. A powerful and accessible deconvolution method woul ...

We consider the idealized setting of gradient flow on the population risk for infinitely wide two-layer ReLU neural networks (without bias), and study the effect of symmetries on the learned parameters and predictors. We first describe a general class of s ...

Numerical solution of the involved governing equations confirm that the commonly used two orthogonal sets of gain- and loss-probes in BOTDA, differently affect the evolution of the pump state-of- polarization, thereby potentially compromising the minimizat ...

A unified numerical framework is presented for the modelling of multiphasic viscoelastic and elastic flows. The rheologies considered range from incompressible Newtonian or Oldroyd-B viscoelastic fluids to Neo-Hookean elastic solids. The model is formulate ...

The accurate investigation of many geophysical phenomena via direct numerical simulations is computationally not possible nowadays due to the huge range of spatial and temporal scales to be resolved. Therefore advances in this field rely on the development ...

We propose a physics-informed neural network (PINN) as the forward model for tomographic reconstructions of biological samples. We demonstrate that by training this network with the Helmholtz equation as a physical loss, we can predict the scattered field ...

This thesis consists of three applications of machine learning techniques to empirical asset pricing. In the first part, which is co-authored work with Oksana Bashchenko, we develop a new method that detects jumps nonparametrically in financial time series ...

In labscale Faraday experiments, meniscus waves respond harmonically to small-amplitude forcing without threshold, hence potentially cloaking the instability onset of parametric waves. Their suppression can be achieved by imposing a contact line pinned at ...

Transfer learning can signiﬁcantly improve the sample eﬃciency of neural networks, by exploiting the relatedness between a data-scarce target task and a data-abundant source task. Despite years of successful applications, transfer learning practice often r ...

The use of model-based numerical simulations of wave propagation in rooms for engineering applications requires that acoustic conditions for multiple parameters are evaluated iteratively, which is computationally expensive. We present a reduced basis metho ...

Time series with missing data are signals encountered in important settings for machine learning. Some of the most successful prior approaches for modeling such time series are based on recurrent neural networks that transform the input and previous state ...

We address the problem of designing stabilizing control policies for nonlinear systems in discrete-time, while minimizing an arbitrary cost function. When the system is linear and the cost is convex, the System Level Synthesis (SLS) approach offers an effe ...

Theoretical and computational approaches to the study of materials and molecules have, over the last few decades, progressed at an exponential rate. Yet, the possibility of producing numerical predictions that are on par with experimental measurements is t ...

In digital imaging, especially in the process of data acquisition and transmission, images are often affected by impulsive noise. Therefore, it is essential to remove impulsive noise from images before any further processing. Due to the remarkable performa ...

We study the large deviations of the power injected by the active force for an active Ornstein-Uhlenbeck particle (AOUP), free or in a confining potential. For the free-particle case, we compute the rate function analytically in d-dimensions from a saddle- ...

The amount of study on Quantum Machine Learning (QML) is increasing extensively due to its potential advantages in terms of representational power and computational resources. These advances suggest a possibility to extend its usage into the context of Ear ...

This paper deals with the mathematical model that describes the function of the human heart. More specifically, it addresses the equations that express the electromechanical process, that is the mechanical deformation (contraction and relaxation) of the he ...

Learning Dynamics of Spring-Mass Models with Physics-Informed Graph Neural Networks

Chat with Graph Search

TCB-spline-based isogeometric analysis method with high-quality parameterizations

Role of stochastic noise and generalization error in the time propagation of neural-network quantum states

Augmented Lagrangian Methods for Provable and Scalable Machine Learning

Deep learning-based galaxy image deconvolution

On the symmetries in the dynamics of wide two-layer neural networks

Numerical Studies of Brillouin-induced Polarization Pulling of Probe and Pump in Weakly-Birefringent Optical fibers with Applications to BOTDA

Numerical simulation of immiscible incompressible viscous, viscoelastic and elastic multiphase flows

Exploiting Marginal Stability in Slow-Fast Quasilinear Dynamical Systems

Physics-informed neural networks for diffraction tomography

Essays in Empirical Asset Pricing

Subharmonic parametric instability in nearly brimful circular cylinders: a weakly nonlinear analysis

Probing transfer learning with a model of synthetic correlated datasets

Reduced basis methods for numerical room acoustic simulations with parametrized boundaries

Recursive Input And State Estimation: A General Framework For Learning From Time Series With Missing Data

Neural System Level Synthesis: Learning over All Stabilizing Policies for Nonlinear Systems

Physics-enhanced machine learning with symmetry-adapted and long-range representations

Impulsive noise removal via a blind CNN enhanced by an iterative post-processing

Work fluctuations in the active Ornstein-Uhlenbeck particle model

Quantum Convolutional Circuits For Earth Observation Image Classification

Mathematical and numerical models for the cardiac electromechanical function