轻量量子循环单元在参数量上远低于经典与量子模型
A Quantum Variational Approach to Prototypical Recurrent Unit
- 用量子变分电路设计紧凑的原型循环单元
- 参数量少于LSTM/GRU/QLSTM/QGRU，预测性能相当
- 适合需要低资源、高可扩展性的时序建模任务
我们提出一种轻量级量子原型循环单元（QPRU），其参数量显著少于经典循环结构（如长短期记忆网络LSTM和门控循环单元GRU）以及量子变体（如量子LSTM QLSTM和量子GRU QGRU）。尽管结构紧凑，QPRU在预测性能上仍可媲美当前最优基准，同时具备更好的可扩展性与更少的可训练参数，具有重要的结构与实用优势。
原文摘要 · Abstract (English)
We introduce a lightweight Quantum Prototypical Recurrent Unit (QPRU) that requires significantly fewer parameters than both classical recurrent architectures, such as Long Short- Term Memory (LSTM) and Gated Recurrent Unit (GRU), and quantum variants, including Quantum LSTM (QLSTM) and Quantum GRU (QGRU). Despite its compact design, the QPRU achieves competitive forecasting performance, matching state-of-the-art baselines while offering important structural and practical advantages, including enhanced scalability and a reduced number of trainable parameters.
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。