analiza aiqbench
This paper advances Quantum Recurrent Neural Networks by addressing the computational complexity of amplitude encoding through a novel pre-processing technique and a circuit architecture that reduces depth while maintaining mathematical equivalence. By improving generalization on real-world datasets, the work offers practical pathways for enhancing quantum resource efficiency in time series forecasting applications. The approach bridges a gap between theoretical encoding strategies and deployable quantum machine learning models.
Improving Quantum Recurrent Neural Networks with Amplitude Encoding
arXiv:2508.16784v3 Announce Type: replace Abstract: Quantum machine learning holds promise for advancing time series forecasting. The Quantum Recurrent Neural Network (QRNN), inspired by classical RNNs, encodes temporal data into quantum states that are periodically input into a quantum circuit. While prior QRNN work has predominantly used angle encoding, alternative encoding strategies like amplitude encoding remain underexplored due to their high computational complexity. In this paper, we evaluate and improve amplitude-based QRNNs using EnQode, a recently introduced method for approximate amplitude encoding. We propose a simple pre-processing technique that augments amplitude encoded inputs with their pre-normalized magnitudes, leading to improved generalization on two real world data sets. Additionally, we introduce a novel circuit architecture for the QRNN that is mathematically equivalent to the original model but achieves a substantial reduction in circuit depth. Together, these contributions demonstrate practical improvements to QRNN design in both model performance and quantum resource efficiency.
Abstract:Quantum machine learning holds promise for advancing time series forecasting. The Quantum Recurrent Neural Network (QRNN), inspired by classical RNNs, encodes temporal data into quantum states that are periodically input into a quantum circuit. While prior QRNN work has predominantly used angle encoding, alternative encoding strategies like amplitude encoding remain underexplored due to their high computational complexity. In this paper, we evaluate and improve amplitude-based QRNNs using EnQode, a recently introduced method for approximate amplitude encoding. We propose a simple pre-processing technique that augments amplitude encoded inputs with their pre-normalized magnitudes, leading to improved generalization on two real world data sets. Additionally, we introduce a novel circuit architecture for the QRNN that is mathematically equivalent to the original model but achieves a substantial reduction in circuit depth. Together, these contributions demonstrate practical improvements to QRNN design in both model performance and quantum resource efficiency.
arXiv:2508.16784 [quant-ph]
(or arXiv:2508.16784v3 [quant-ph] for this version)
Text integral sub licența deschisă a publicației · 152 cuvinte
Subiecte conexe
Improving Quantum Recurrent Neural Networks with Amplitude Encoding
arXiv · 14 oct. 2026
[AINews] High Taste Testers Ep. 1
Latent Space · 17 oct. 2026
WiMi’s Quantum Circuits Boost Image Recognition Efficiency
Quantum Zeitgeist · 28 mai 2026
QTN-RQNN: Quantum Tensor Network-Based Recurrent Quantum Neural Network
arXiv · 12 oct. 2026