Skip to content
Back Home
  • Home
  • The Chair
    • About
    • Our Head
    • Our Team
    • Past Members
    • Contact
  • Research
    • Publications
    • Projects
    • Teaching
    • Initiatives
    • Posts on Math and Research
    • Contributors
  • Join us!
    • Jobs board
    • Upcoming events
    • Past Events
  • Resources
    • Seminars
    • Math to go!
    • Akademy
    • GitHub
  • Search
Back Home
  • Search
  • Home
  • The Chair
    • About
    • Our Head
    • Our Team
    • Past Members
    • Contact
  • Research
    • Publications
    • Projects
    • Teaching
    • Initiatives
    • Posts on Math and Research
    • Contributors
  • Join us!
    • Jobs board
    • Upcoming events
    • Past Events
  • Resources
    • Seminars
    • Math to go!
    • Akademy
    • GitHub
Home » Hub » Robust neural ODEs

Robust neural ODEs

Published June 20, 2022

The code implements the gradient regularization method of robust training in the setting of neural ODEs.
Various jupyter notebooks are included that generate plots comparing standard to robust training for 2d point clouds.

Code:

A good starting point is robustness_plots.ipynb

Code is based on GitHub: borjanG : 2021-dynamical-systems that uses the torchdiffeq package GitHub : rtqichen: torchdiffeq

 

|| Go to the Math & Research main page

You may also like

Published July 23, 2022

Lloyd’s Algorithm

Author: Martín Hernández, FAU DCN-AvH Code: In this repository, we show a code for Lloyd’s algorithm. Also called Voronoid iteration, this is […]

Published December 20, 2022

Federated Learning: Protect your data and privacy

Federated Learning: Protect your data and privacy Code: A basic PyTorch implementation of the FedAvg algorithm (GitHub) Federated Learning is becoming an […]

Published April 7, 2022

The interplay of control and deep learning

Author: Borjan Geshkovski, MIT The interplay of control and Deep Learning By Borjan Geshkovski   It is superfluous to state the impact […]

Published September 30, 2022

Approximating the 1D wave equation using Physics Informed Neural Networks (PINNs)

Approximating the 1D wave equation using Physics Informed Neural Networks (PINNs) Code: • See the complete report by Dania Sana   Introduction […]

Post navigation

  • Previous post Optimal design of sensors and actuators by E. Zuazua
  • Back to post list
  • Next post Mini-workshop: “Recent Advances in Analysis and Control”
Last news
  • Mini-workshop: Analysis, Numerics and Control
  • Convolutional autoencoders for very low-dimensional parametrizations of nonlinear fluid flow
  • Open position for Chair Secretary
  • Event-Triggered Control Using a Positive Systems Approach
  • Shape optimization problems in thermal insulation with thin insulating layers

©  2019 - 2023  – All rights reserved - FAU DCN-AvH Chair for Dynamics, Control and Numerics - Alexander von Humboldt Professorship at Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany Imprint | Privacy | Accessibility | Contact