/sysid-neural-unc

Code of the paper "Neural state-space models: Empirical evaluation of uncertainty quantification"

Primary LanguagePython

Neural state-space models: Empirical evaluation of uncertainty quantification

This repository contains the Python code to reproduce the results of the paper Neural state-space models: Empirical evaluation of uncertainty quantification by Marco Forgione and Dario Piga, accepted for presentation at the 2023 IFAC World Congress.

Folders:

The examples discussed in the paper are:

Software requirements:

Experiments were performed on a Python 3.10 conda environment with

  • numpy
  • scipy
  • matplotlib
  • pandas
  • pytorch (version 1.12)
  • functorch (version 0.2.0)

These dependencies may be installed through the commands:

conda install numpy scipy pandas matplotlib
conda install pytorch -c pytorch
pip install functorch

To run the software, please make sure that this repository's root folder is added to your PYTHONPATH.