Quantum Long Short-Term Memory

2020/09/03 by Samuel Yen-Chi Chen, Shinjae Yoo, Chen, Samuel Yen-Chi +3 · 24 citations
Computer Science · Engineering · #Advancements in Semiconductor Devices and Circuit Design #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Neural Networks and Reservoir Computing #Quantum Computing Algorithms and Architecture #Quantum Physics (quant-ph)

paper · pdf · doi:10.48550/arxiv.2009.01783

openalex publication_date 2020/09/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Long short-term memory (LSTM) is a kind of recurrent neural networks (RNN) for sequence and temporal dependency data modeling and its effectiveness has been extensively established. In this work, we propose a hybrid quantum-classical model of LSTM, which we dub QLSTM. We demonstrate that the proposed model successfully learns several kinds of temporal data. In particular, we show that for certain testing cases, this quantum version of LSTM converges faster, or equivalently, reaches a better accuracy, than its classical counterpart. Due to the variational nature of our approach, the requirements on qubit counts and circuit depth are eased, and our work thus paves the way toward implementing machine learning algorithms for sequence modeling on noisy intermediate-scale quantum (NISQ) devices.

Cited by

• Multivariate Time Series Forecasting with Adaptive Non-Local Observables
• Batched Training for QLSTM vs. QFWP: A System-Oriented Approach to EPC-Aware RMSE-DA
• QKAN-LSTM: Quantum-inspired Kolmogorov-Arnold Long Short-term Memory
• Opportunities and Challenges for Data Quality in the Era of Quantum Computing
• Neural Architecture Search for Quantum Autoencoders
• Lane-Frame Quantum Multimodal Driving Forecasts for the Trajectory of Autonomous Vehicles
• Hybrid Quantum-Classical Selective State Space Artificial Intelligence
• Hybrid Quantum-Classical Recurrent Neural Networks
• Sustainable NARMA-10 Benchmarking for Quantum Reservoir Computing
• Complementary Matrix-Gated QKAN Fast-Weight Programmers for Quantum Dynamics Forecasting
• QLook:Quantum-Driven Viewport Prediction for Virtual Reality
• Prediction of Stocks Index Price using Quantum GANs
• Quantum-Enhanced Forecasting for Deep Reinforcement Learning in Algorithmic Trading
• Improving Quantum Recurrent Neural Networks with Amplitude Encoding
• Quantum Machine Learning and Grover's Algorithm for Quantum Optimization of Robotic Manipulators
• Quantum Machine Learning for UAV Swarm Intrusion Detection
• Breaking Through Barren Plateaus: Reinforcement Learning Initializations for Deep Variational Quantum Circuits
• Quantum Long Short-term Memory with Differentiable Architecture Search
• Préface
• Q-DPTS: Quantum Differentially Private Time Series Forecasting via Variational Quantum Circuits
• Benchmarking Quantum and Classical Sequential Models for Urban Telecommunication Forecasting
• Quantum Temporal Fusion Transformer
• Quantum generative modeling for financial time series with temporal correlations
• PennyCoder: Efficient Domain-Specific LLMs for PennyLane-Based Quantum Code Generation

Related

• Quantum Kernel-Based Long Short-term Memory
• Implementation Guidelines and Innovations in Quantum LSTM Networks
• A Novel Stochastic LSTM Model Inspired by Quantum Machine Learning
• Quantum Long Short-Term Memory for Drug Discovery
• Quantum Long Short-term Memory with Differentiable Architecture Search