用于分子性质预测的相干Floquet量子储层
Coherent Floquet quantum reservoirs for molecular property prediction
浏览论文内容
中文总结 AI 辅助
本文提出基于离散时间晶体的相干Floquet量子储层架构，用于分子性质预测，在分类和带隙预测任务上优于回声状态网络，并在超导量子云平台上验证了其鲁棒性。
中文摘要 AI 辅助
量子储层计算（QRC）利用量子动力学来表示输入历史，通过训练好的经典读出进行预测。离散时间晶体（DTC）在周期性驱动下表现出稳健的次谐波响应，先前的工作已利用其动力学构建了DTC-QRC。在此，我们构建了一种基于DTC的储层架构，用于从结构和动力学观测中预测分子性质。相干Floquet演化处理局部分子图事件和表面跳跃轨迹，而受控重置则调节早期输入的贡献。每个输入序列末尾的测量产生固定维度的特征向量。训练好的经典解码器利用该向量进行抑制剂活性和血脑屏障通透性分类以及电子带隙预测，而储层参数在训练期间保持固定。在匹配输入长度和输出宽度的情况下，DTC-QRC在长前缀图分类和所研究的乙烯带隙预测任务上优于回声状态网络。退相干降低了两种应用的性能，这与相干传播的作用一致。在Quafu超导量子云平台上的实验表明，成对可观测量在器件噪声下保留了任务信息。该架构为使用量子储层计算进行分子筛选和时间分辨性质预测提供了一个通用框架。
英文摘要
Quantum reservoir computing (QRC) uses quantum dynamics to represent input histories for prediction through a trained classical readout. Discrete time crystals (DTCs) exhibit robust subharmonic responses under periodic driving, and previous work has used their dynamics to construct DTC-QRC. Here we construct a DTC-based reservoir architecture to predict molecular properties from structural and dynamical observations. Coherent Floquet evolution processes local molecular graph events and surface-hopping frames, while controlled reset regulates the contribution of earlier inputs. Measurements at the end of each input sequence yield a feature vector of fixed dimension. Trained classical decoders use this vector for inhibitor-activity and blood--brain-barrier permeability classification and electronic-gap forecasting, while the reservoir parameters remain fixed during training. With matched input lengths and output widths, DTC-QRC outperforms echo-state networks on long-prefix graph classification and the studied ethene gap forecasting tasks. Dephasing lowers performance in both applications, consistent with a role for coherent propagation. Experiments on the Quafu superconducting quantum cloud platform show that pair observables retain task information under device noise. The architecture provides a common framework for molecular screening and time-resolved property prediction using quantum reservoir computing.
发表机构
- Beijing Institute of Technology（北京理工大学）
- Shandong University（山东大学）
机构由 AI 辅助整理，请以论文原文为准。
