量子储层计算在时间序列预测中表现不俗，且更节能。
Sustainable NARMA-10 Benchmarking for Quantum Reservoir Computing
- 用量子储层计算处理非线性自回归移动平均任务
- 准确率与经典模型相当，但计算资源消耗更低
- 适合资源受限环境下的可持续人工智能应用
本研究对比了量子储层计算（QRC）与经典模型（如回声状态网络ESNs、长短期记忆网络LSTMs）及混合量子-经典架构（QLSTM）在非线性自回归移动平均任务（NARMA-10）上的表现。评估指标包括预测精度（NRMSE）、计算成本和评估时间。结果表明，QRC在保持竞争性准确率的同时，展现出潜在的可持续优势，尤其在资源受限场景下，凸显其在可持续时间序列人工智能应用中的前景。
原文摘要 · Abstract (English)
This study compares Quantum Reservoir Computing (QRC) with classical models such as Echo State Networks (ESNs) and Long Short-Term Memory networks (LSTMs), as well as hybrid quantum-classical architectures (QLSTM), for the nonlinear autoregressive moving average task (NARMA-10). We evaluate forecasting accuracy (NRMSE), computational cost, and evaluation time. Results show that QRC achieves competitive accuracy while offering potential sustainability advantages, particularly in resource-constrained settings, highlighting its promise for sustainable time-series AI applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。