量子时序学习新模型，自调节权重提升稳定性和预测精度
Self-Modulating Quantum Fast-Weight Programmers for Efficient Adaptive Sequential Learning
- 通过自适应调制新旧权重更新，增强记忆与信息融合能力
- 在不同量子比特数和序列长度下均实现更优收敛与预测性能
- 适合研究量子机器学习中时序数据处理的学者参考
近期量子机器学习的发展推动了序列数据处理高效模型的研究。本文提出自调制量子快速权重编程器（Self-Modulating QFWP），在量子快速权重编程基础上，引入对新生成权重更新与历史权重记忆的自适应调制机制。数值实验表明，该方法在不同量子比特数量和输入序列长度条件下，均提升了收敛稳定性与预测性能。我们进一步提供了理论分析，说明自调制如何平衡新信息注入与记忆保留，从而增强时间信息传播。结果表明，Self-Modulating QFWP 是一种紧凑且高效的量子机器学习框架，适用于时间序列数据处理。
原文摘要 · Abstract (English)
Recent advances in quantum machine learning have motivated efficient models for sequential data processing. In this paper, we propose Self-Modulating Quantum Fast Weight Programmers, or Self-Modulating QFWP, which extends Quantum Fast Weight Programmers by introducing adaptive modulation over both newly generated fast-weight updates and historical fast-weight memory. Numerical results show that the proposed mechanism improves convergence stability and prediction performance across varying model settings, including different numbers of qubits and input sequence lengths. We further provide theoretical arguments explaining how self-modulation balances new information injection with memory retention, thereby enhancing temporal information propagation. These results suggest that Self-Modulating QFWP is a compact and effective framework for quantum machine learning on time-series data.
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。