Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Maragkopoulos, G., Stefanakos, N., Mandilara, A., Syvridis, D.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.06892
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913786226540544
author Maragkopoulos, G.
Stefanakos, N.
Mandilara, A.
Syvridis, D.
author_facet Maragkopoulos, G.
Stefanakos, N.
Mandilara, A.
Syvridis, D.
contents We combine classical and quantum Machine Learning (ML) techniques to effectively analyze long time-series data acquired during experiments. Specifically, we demonstrate that replacing a deep classical neural network with a thoughtfully designed Variational Quantum Circuit (VQC) in an ML pipeline for multiclass classification of time-series data yields the same classification performance, while significantly reducing the number of trainable parameters. To achieve this, we use a VQC based on a single qudit, and encode the classical data into the VQC via a trainable hybrid autoencoder which has been recently proposed as embedding technique. Our results highlight the importance of tailored data pre-processing for the circuit and show the potential of qudit-based VQCs.
format Preprint
id arxiv_https___arxiv_org_abs_2504_06892
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Applications of Hybrid Machine Learning Methods to Large Datasets: A Case Study
Maragkopoulos, G.
Stefanakos, N.
Mandilara, A.
Syvridis, D.
Quantum Physics
We combine classical and quantum Machine Learning (ML) techniques to effectively analyze long time-series data acquired during experiments. Specifically, we demonstrate that replacing a deep classical neural network with a thoughtfully designed Variational Quantum Circuit (VQC) in an ML pipeline for multiclass classification of time-series data yields the same classification performance, while significantly reducing the number of trainable parameters. To achieve this, we use a VQC based on a single qudit, and encode the classical data into the VQC via a trainable hybrid autoencoder which has been recently proposed as embedding technique. Our results highlight the importance of tailored data pre-processing for the circuit and show the potential of qudit-based VQCs.
title Applications of Hybrid Machine Learning Methods to Large Datasets: A Case Study
topic Quantum Physics
url https://arxiv.org/abs/2504.06892