Simulation and AI
From parameter estimation for simulators to full-fledged digital twins, AI promises faster development and reduced modelling effort. The truth is however nuanced and practical applications are not so straightforward as one would like.

All content in this series

Pill

Physics-informed DeepONets

Physics-informed DeepONets can learn the solution operator of arbitrary partial differential equations, even without any paired …

Samuel
Simulation and AI
Pill

Learning nonlinear operators: the DeepONet architecture

The universal approximation theorem for operators suggests a neural network architecture for learning continuous nonlinear operators, called …

Samuel
Simulation and AI
Pill

Brax - A Differentiable Physics Engine for Large Scale Rigid Body Simulation

The development of versatile robots demands a better understanding of physics simulators. A recent line of research focuses on engines whose …

A photo of Fabio
Simulation and AI
Pill

Simulation in Robotics Opportunities Challenges Suggestions

Despite great advancements in physics based simulators for robotics over the last few years, a big sim2real gap remains in the performance …

A photo of Fabio
Simulation and AI
Blog

Solving PDEs With Neural Networks

We discuss some current trends in applying ML to the solution of differential equations, and the difficulties faced. We focus on a family of …

A picture of Omer A picture of Miguel
Simulation and AI
Seminar

Solving Schrödinger's equation with neural networks

In this work, we attempt to solve the Time Dependent Schrödinger Equation directly by placing a neural network ansatz on the solution and …

A picture of Omer
Simulation and AI
Seminar

Solving PDEs with neural networks

We’ll be talking about PDEs and how to solve them numerically using NNs. If you have no idea what those are you should probably read a …

A picture of Omer
Simulation and AI

Other series in Advances and fundamentals in ML

Deep Learning on Functional Data

Much of the data we encounter in everyday life is functional in nature. Examples include weather data, outputs from computer simulations, …

1 item

Error estimation and model selection

Correct model selection requires careful data handling and attention to iterative or cyclic design / deployment procedures, as are the norm …

1 item

Diffusion Models

Diffusion models (DM) have become the state of the art for sample quality in generative modelling. They work by sequentially corrupting …

8 items

Geometric deep learning

Specialized deep learning architectures exploit the intrinsic regularities arising from the underlying structure of the physical world. …

3 items
Check all of our work