Skip to content

【代码贡献】新增 QuantumReservoir 量子储备池计算模块 - #83

Open
tokenjunkielabs wants to merge 1 commit into
OriginQ:developfrom
woahwhattheheck:zz-sol-verdigris-94027/origin-cup-quantum-reservoir-20260920
Open

tokenjunkielabs wants to merge 1 commit into
OriginQ:developfrom
woahwhattheheck:zz-sol-verdigris-94027/origin-cup-quantum-reservoir-20260920

Conversation

@tokenjunkielabs

Copy link
Copy Markdown

关联 #13(2026 本源杯开源创新赛道|代码贡献)。

新增 pyqpanda_alg.QuantumReservoir,提供完整的量子储备池计算(Quantum Reservoir Computing, QRC)工作流:

  • 固定随机量子储备池:输入特征通过 RY 循环编码,叠加固定 RX/RZ 动力学与环形 ZZ 相互作用;
  • ReservoirConfig + 可持久化 ReservoirParameters,seed 固定后训练/推理复用同一量子特征映射;
  • 明确的测量契约:每个量子比特 Z 期望值 + 最近邻环形 ZZ 相关;
  • reservoir_feature_vector / reservoir_feature_matrix 将后端测量结果稳定转换为经典特征;
  • RidgeReadout 提供带非正则化截距的闭式岭回归,支持单输出和多输出;
  • QuantumReservoirRegressor 将电路构造、测量特征和经典训练接口组合成可复用 API;
  • PyQPanda3 延迟导入,经典特征与读出训练不依赖量子后端初始化;
  • 配套 docs/QuantumReservoir.md 与 Tutorials/QuantumReservoir_example.py。

设计目标是把量子部分保持为固定、可重复使用的非线性特征映射,只训练廉价的经典读出层,适用于时间序列回归、非线性系统辨识、传感器流等场景;实际 shot 分配、误差缓解、转译与设备校准继续由调用方后端负责。

Source head: bc0b60f
Base: develop@5f973efccb84bc193157d1ccebe32137e307293b

No test run is claimed; submission scope is the algorithm module, package API, documentation, and runnable example.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants