---
license: mit
---

<div align="center">

# Neural Continuous-Discrete State Space Models (NCDSSM) 

[![preprint](https://img.shields.io/static/v1?label=arXiv&message=2301.11308&color=B31B1B)](https://arxiv.org/abs/2301.11308)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Venue:ICML 2023](https://img.shields.io/badge/Venue-ICML%202023-007CFF)](https://icml.cc/)

</div>

<p align="center">
  <img src="./assets/ncdssm.webp" width="30%">
  <br />
  <span>Fig 1. (Top) Generative model of Neural Continuous-Discrete State Space Model. (Bottom) Amortized inference for auxiliary variables and continuous-discrete Bayesian inference for states.</span>
</p>

____
This repository contains pretrained checkpoints for reproducing the experiments presented in the ICML 2023 paper [*Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series*](https://arxiv.org/abs/2301.11308). For details on how to use these checkpoints, please refer to https://github.com/clear-nus/NCDSSM.