用量子门的纠缠与解纠缠能力模拟记忆遗忘，构建新型量子循环网络。
Quantum RNNs and LSTMs Through Entangling and Disentangling Power of Unitary Transformations
- 利用酉变换的纠缠/解纠缠能力建模记忆保留与遗忘机制
- 揭示纠缠在量子神经网络训练中的核心优化作用
- 为实际应用设计更优量子电路提供新思路
本文提出一种基于Linden等人（2009）核心思想的量子循环神经网络（RNN）及增强版长短期记忆（LSTM）网络建模框架，其中研究了酉变换的纠缠与解纠缠能力。特别地，将纠缠与解纠缠视为LSTM中的信息保留与遗忘机制。因此，纠缠成为优化（训练）过程的关键组成部分。我们认为，通过利用对酉变换纠缠能力的先验知识，所提出的量子-经典混合框架可指导各类实际应用中更优参数化量子电路的设计。
原文摘要 · Abstract (English)
In this paper, we present a framework for modeling quantum recurrent neural networks (RNNs) and their enhanced version, long short-term memory (LSTM) networks using the core ideas presented by Linden et al. (2009), where the entangling and disentangling power of unitary transformations is investigated. In particular, we interpret entangling and disentangling power as information retention and forgetting mechanisms in LSTMs. Thus, entanglement emerges as a key component of the optimization (training) process. We believe that, by leveraging prior knowledge of the entangling power of unitaries, the proposed quantum-classical framework can guide the design of better-parameterized quantum circuits for various real-world 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。