科研 Skill
量子机器学习框架
pennylane
Trains quantum circuits with autodiff across IBM/Google/Rigetti/IonQ devices: VQE, QAOA, hybrid models with PyTorch/JAX. Use for gradient-based variational quantum algorithms.
SKILL.md
PennyLane
Overview
PennyLane is a quantum computing library that enables training quantum computers like neural networks. It provides automatic differentiation of quantum circuits, device-independent programming, and seamless integration with classical machine learning frameworks.
Installation
PennyLane 0.45.0 requires Python 3.11 or newer. Install using uv with pinned versions for reproducible environments:
uv pip install "pennylane==0.45.0"
For quantum hardware access, install the plugin matching the target provider. Start from a clean environment when adding or upgrading Qiskit because its dependency graph is strict.
# IBM Quantum
uv pip install "pennylane-qiskit==0.45.0"
# Amazon Braket
uv pip install "amazon-braket-pennylane-plugin==1.34.1"
# Google Cirq
uv pip install "pennylane-cirq==0.44.0"
# Rigetti Forest
uv pip install "pennylane-rigetti==0.40.0"
# IonQ
uv pip install "pennylane-ionq==0.45.0"
# High-performance local simulators
uv pip install "pennylane-lightning==0.45.0"
# Catalyst JIT compilation
uv pip install "pennylane-catalyst==0.15.0"
Quick Start
Build a quantum circuit and optimize its parameters:
import pennylane as qml
from pennylane import numpy as np
# Create device
dev = qml.device('default.qubit', wires=2)
# Define quantum circuit
@qml.qnode(dev)
def circuit(params):
qml.RX(params[0], wires=0)
qml.RY(params[1], wires=1)
qml.CNOT(wires=[0, 1])
return qml.expval(qml.PauliZ(0))
# Optimize parameters
opt = qml.GradientDescentOptimizer(stepsize=0.1)
params = np.array([0.1, 0.2], requires_grad=True)
for i in range(100):
params = opt.step(circuit, params)
Core Capabilities
1. Quantum Circuit Construction
Build circuits with gates, measurements, and state preparation. See references/quantum_circuits.md for:
- Single and multi-qubit gates
- Controlled operations and conditional logic
- Mid-circuit measurements and adaptive circuits
- Various measurement types (expectation, probability, samples)
- Circuit inspection and debugging
2. Quantum Machine Learning
Create hybrid quantum-classical models. See references/quantum_ml.md for:
- Integration with PyTorch and JAX
- Quantum neural networks and variational classifiers
- Data encoding strategies (angle, amplitude, basis, IQP)
- Training hybrid models with backpropagation
- Transfer learning with quantum circuits
3. Quantum Chemistry
Simulate molecules and compute ground state energies. See references/quantum_chemistry.md for:
- Molecular Hamiltonian generation
- Variational Quantum Eigensolver (VQE)
- UCCSD ansatz for chemistry
- Geometry optimization and dissociation curves
- Molecular property calculations
4. Device Management
Execute on simulators or quantum hardware. See references/devices_backends.md for:
- Built-in simulators (default.qubit, lightning.qubit, default.mixed)
- Hardware plugins (IBM, Amazon Braket, Google, Rigetti, IonQ)
- Device selection and configuration
- Performance optimization and caching
- GPU acceleration and JIT compilation
5. Optimization
Train quantum circuits with various optimizers. See references/optimization.md for:
- Built-in optimizers (Adam, gradient descent, momentum, RMSProp)
- Gradient computation methods (backprop, parameter-shift, adjoint)
- Variational algorithms (VQE, QAOA)
- Training strategies (learning rate schedules, mini-batches)
- Handling barren plateaus and local minima
6. Advanced Features
Leverage templates, transforms, and compilation. See references/advanced_features.md for:
- Circuit templates and layers
- Transforms and circuit optimization
- Pulse-level programming
- Catalyst JIT compilation
- Noise models and error mitigation
- Resource estimation
Common Workflows
Train a Variational Classifier
# 1. Define ansatz
@qml.qnode(dev)
def classifier(x, weights):
# Encode data
qml.AngleEmbedding(x, wires=range(4))
# Variational layers
qml.StronglyEntanglingLayers(weights, wires=range(4))
return qml.expval(qml.PauliZ(0))
# 2. Train
opt = qml.AdamOptimizer(stepsize=0.01)
weights = np.random.random((3, 4, 3)) # 3 layers, 4 wires
for epoch in range(100):
for x, y in zip(X_train, y_train):
weights = opt.step(lambda w: (classifier(x, w) - y)**2, weights)
Run VQE for Molecular Ground State
from pennylane import qchem
# 1. Build Hamiltonian
symbols = ['H', 'H']
geometry = np.array([[0.0, 0.0, -0.66140414], [0.0, 0.0, 0.66140414]])
molecule = qchem.Molecule(symbols, geometry)
H, n_qubits = qchem.molecular_hamiltonian(molecule)
hf_state = qchem.hf_state(electrons=2, orbitals=n_qubits)
singles, doubles = qchem.excitations(electrons=2, orbitals=n_qubits)
s_wires, d_wires = qchem.excitations_to_wires(singles, doubles)
# 2. Define ansatz
@qml.qnode(dev)
def vqe_circuit(params):
qml.BasisState(hf_state, wires=range(n_qubits))
qml.UCCSD(params, wires=range(n_qubits), s_wires=s_wires, d_wires=d_wires)
return qml.expval(H)
# 3. Optimize
opt = qml.AdamOptimizer(stepsize=0.1)
params = np.zeros(len(singles) + len(doubles), requires_grad=True)
for i in range(100):
params, energy = opt.step_and_cost(vqe_circuit, params)
print(f"Step {i}: Energy = {energy:.6f} Ha")
Switch Between Devices
# Same circuit, different backends
circuit_def = lambda dev: qml.qnode(dev)(circuit_function)
# Test on simulator
dev_sim = qml.device('default.qubit', wires=4)
result_sim = circuit_def(dev_sim)(params)
# Run on quantum hardware
from qiskit_ibm_runtime import QiskitRuntimeService
service = QiskitRuntimeService()
backend = service.least_busy(operational=True, simulator=False, min_num_qubits=4)
dev_hw = qml.device('qiskit.remote', wires=backend.num_qubits, backend=backend)
result_hw = circuit_def(dev_hw)(params)
Detailed Documentation
For comprehensive coverage of specific topics, consult the reference files:
- Getting started:
references/getting_started.md- Installation, basic concepts, first steps - Quantum circuits:
references/quantum_circuits.md- Gates, measurements, circuit patterns - Quantum ML:
references/quantum_ml.md- Hybrid models, framework integration, QNNs - Quantum chemistry:
references/quantum_chemistry.md- VQE, molecular Hamiltonians, chemistry workflows - Devices:
references/devices_backends.md- Simulators, hardware plugins, device configuration - Optimization:
references/optimization.md- Optimizers, gradients, variational algorithms - Advanced:
references/advanced_features.md- Templates, transforms, JIT compilation, noise
Best Practices
- Start with simulators - Test on
default.qubitbefore deploying to hardware - Use parameter-shift for hardware - Backpropagation only works on simulators
- Choose appropriate encodings - Match data encoding to problem structure
- Initialize carefully - Use small random values to avoid barren plateaus
- Monitor gradients - Check for vanishing gradients in deep circuits
- Cache devices - Reuse device objects to reduce initialization overhead
- Profile circuits - Use
qml.specs()to analyze circuit complexity - Test locally - Validate on simulators before submitting to hardware
- Use templates - Leverage built-in templates for common circuit patterns
- Compile when possible - Use Catalyst JIT for performance-critical code
Resources
- Official documentation: https://docs.pennylane.ai
- Codebook (tutorials): https://pennylane.ai/codebook
- QML demonstrations: https://pennylane.ai/qml/demonstrations
- Community forum: https://discuss.pennylane.ai
- GitHub: https://github.com/PennyLaneAI/pennylane
示例提示词
我想用PennyLane训练一个变分量子线路做VQE能量优化。
所属插件
安装该插件会一并获得同领域的 22 个 Skill / MCP。
同插件的其他科研 Skill
- 天文星表检索Queries astronomical archives (Gaia, SDSS, VizieR, MAST, NED, SIMBAD) via astroquery/TAP/ADQL and cross-matches results. Use when sourcing or combining survey data by position.
- 天文光谱分析Reduces 1D astronomical spectra with specutils: continuum normalization, line fitting, redshift/radial-velocity measurement, equivalent widths. Use for spectral classification or velocity work.
- 天文观测数据分析Runs applied astronomy pipelines with astropy/astroquery: catalog cross-matching, Gaia/SIMBAD queries, aperture photometry, CMB power spectra. Use for end-to-end data-analysis workflows.
- Astropy天文数据处理Covers core Astropy APIs for units, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use as the API reference, before reaching for applied workflows.
- 谷歌量子计算框架Builds noise-aware quantum circuits for Google Quantum AI hardware and runs characterization experiments. Use for Google-hardware targeting; use qiskit for IBM or pennylane for differentiable ML.
- 有限元法求解偏微分方程Solves PDEs with finite elements using FEniCS/dolfinx: weak forms, gmsh meshing, Poisson/elasticity problems, boundary conditions, ParaView export. Use for continuum-physics simulation.
- 计算流体力学模拟Runs pseudospectral CFD simulations in Python: Navier-Stokes, shallow water, stratified flows with FFT-based solvers. Use for turbulence, vortex dynamics, or geophysical flow simulation.
- LAMMPS经典分子动力学Runs classical molecular dynamics with LAMMPS: force field selection, NVT/NPT ensembles, RDF/MSD post-processing, OVITO visualization. Use for atomistic materials or molecular simulation.
- 三维科学可视化Creates 3D scientific visualizations with Mayavi: vector fields, isosurfaces, volume rendering, animated 3D plots. Use for visualizing volumetric or vector-field physics data.
- 蒙特卡洛物理模拟Simulates physical systems with Monte Carlo methods: statistical integration, MCMC sampling, the Ising model, error estimation. Use for stochastic physics simulation.
- 地震学数据处理Analyzes seismological data with ObsPy: FDSN waveform download, response removal, phase picking, moment tensor inversion. Use for earthquake and seismic-waveform analysis.
- 粒子图像测速分析Extracts velocity fields from PIV image pairs with OpenPIV: cross-correlation, vector validation, vorticity/strain-rate statistics. Use for experimental fluid-flow measurement.
- 恒星测光分析Performs PSF and aperture photometry with photutils: source detection, PSF fitting, background estimation, multi-epoch light curves. Use for precision stellar photometry beyond one aperture sum.
- 物理信息神经网络Builds physics-informed neural networks, neural ODEs, and data-driven force fields with PyTorch, DeepXDE, torchdiffeq. Use for ML-based physics simulation and surrogate modeling.
- IBM量子计算框架Runs IBM Quantum workflows end to end: Runtime primitives, transpilation, hardware backend selection, error mitigation. Use when targeting IBM Quantum hardware or Runtime.
- Qiskit量子线路实验Implements Qiskit algorithms: circuit construction, VQE/QAOA workflows, noise-model simulation, statevector-vs-shot comparisons. Use for algorithm design and local simulation.
- 开放量子系统模拟Simulates open quantum systems with QuTiP: master equations, Lindblad dynamics, decoherence, cavity QED. Use for open-system physics, not circuit-based quantum computing.
- SciPy数值计算工具Solves ODEs/PDEs, runs FFT analysis, optimization, and sparse linear algebra with SciPy for physics problems. Use as the general-purpose numerical-computing toolkit.
- SymPy符号计算Performs symbolic computation for physics with SymPy: algebra, calculus, Lagrangian mechanics, quantum operators, code generation. Use for exact derivations, not numerical solving.
- 物理量纲与不确定度传播Tracks physical units and propagates measurement uncertainty with pint/uncertainties: GUM budgets, Monte Carlo propagation, dimensionless-group checks. Use to sanity-check a result or unit.
- 多维标注数组NetCDF分析Analyzes labeled multi-dimensional arrays with xarray: NetCDF/HDF5 I/O, lazy Dask loading, rechunking, Zarr stores, CF conventions. Use for gridded scientific data handling.
常见问题
量子机器学习框架能做什么?
Trains quantum circuits with autodiff across IBM/Google/Rigetti/IonQ devices: VQE, QAOA, hybrid models with PyTorch/JAX. Use for gradient-based variational quantum algorithms。
如何安装量子机器学习框架?
在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「量子机器学习框架」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。
量子机器学习框架需要哪些权限?
该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。
量子机器学习框架经过官方审核吗?
是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。