# Implementation and Learning of Quantum Hidden Markov Models

**Authors:** Vanio Markov, Vladimir Rastunkov, Amol Deshmukh, Daniel Fry, Charlee Stefanski  
**arXiv:** [2212.03796](https://arxiv.org/abs/2212.03796)  
**Date:** 2022-12-07  
**Summary page:** https://www.summarizepaper.com/fr/arxiv-id/2212.03796v1/

## Abstract

Hidden Markov models are a powerful tool for learning and describing sequential data. In this work, we focus on understanding the advantages of using quantum hidden Markov models over classical counterparts. We propose a practical, hardware efficient quantum circuit ansatz, as well as a training algorithm. We compare results from executions of these dynamic circuits using quantum simulators with results from IBM quantum hardware.