Triangle Quantum Computing Seminar Series: Improving Quantum Recurrent Neural Networks with Amplitude Encoding

The Duke Quantum Center, the IBM Quantum Innovation Center at NC State, and the UNC Kenan-Flagler's Rethinc. Labs are pleased to present the first Fall Semester Triangle Quantum Computing Seminar on September 5, 2025 at 2 p.m. The UNC Kenan-Flagler Rethinc. Labs welcomes Jack Morgan, to give a talk on "Improving Quantum Recurrent Neural Networks with Amplitude Encoding." --- 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 enhances 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. --- Jack Morgan is a master's student in Applied Data Science at the University of Chicago. He previously earned his B.S. in Physics from Haverford College. For three years he was a Quantum Research Fellow at the Kenan Institute of Private Enterprise, where he developed hybrid quantum-classical algorithms for finance applications. He has authored publications on quantum linear system solvers, asset pricing, and credit risk modeling on quantum processors. His research interests include quantum machine learning, hybrid quantum algorithms, and statistical methods for finance. --- These weekly seminars are virtual. Contact quantumcomputing@ncsu.edu with any questions.