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
Reinforcement learning as a new perspective into controlling physical systems Introduction Optimal control addresses the problem of bringing a system from an […]
Author: Borjan Geshkovski, MIT The interplay of control and Deep Learning By Borjan Geshkovski It is superfluous to state the impact […]
Approximating the 1D wave equation using Physics Informed Neural Networks (PINNs) Introduction Accurate and fast predictions of numerical solutions are of […]
Clustering in pure-attention hardmax transformers and its role in sentiment analysis This post provides an overview of the results in the paper […]
