Time Series forecasting with Quantum Neural Networks

Pegalajar Cuéllar, Manuel; Pegalajar Palomino, María del Carmen; Baca Ruiz, Luis Gonzaga; Cano Gutiérrez, Carlos

doi:10.1007/978-3-031-43085-5_53

Preprint before acceptance (418.7Kb)

Identificadores

URI: https://hdl.handle.net/10481/98138

DOI: 10.1007/978-3-031-43085-5_53

Exportar

Editorial

Springer

Materia

Quantum Neural Networks

Quantum Machine Learning

Time Series Forecasting

Fecha

2023-06-20

Referencia bibliográfica

Cuéllar, M.P., Pegalajar, M.C., Ruiz, L.G.B., Cano, C. (2023). Time Series Forecasting with Quantum Neural Networks. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2023. Lecture Notes in Computer Science, vol 14134. Springer, Cham. https://doi.org/10.1007/978-3-031-43085-5_53

Patrocinador

This article was supported by the project QUANERGY (Ref. TED2021-129360B-I00), Ecological and Digital Transition R&D projects call 2022 funded by MCIN/AEI/10.13039/501100011033 and European Union NextGenerationEU/PRTR, and Grant PID2021-128970OA-I00 by MCIN/AEI/10.13039/501100011033/FEDER

Resumen

In this work we explore the use of Quantum Computing for Time Series forecasting. More speci cally, we design Variational Quantum Circuits as the quantum analogy of feedforward Artificial Neural Networks, and use a quantum neural network pipeline to perform time series forecasting tasks. According to our experiments, our study suggests that Quantum Neural Networks are able to improve results in error prediction while maintaining a lower number of parameters than its classical machine learning counterpart.

Colecciones

OpenAIRE (Open Access Infrastructure for Research in Europe)

Excepto si se señala otra cosa, la licencia del ítem se describe como Attribution-NonCommercial-NoDerivatives 4.0 Internacional