PennyLane Codebook: Interactive Quantum ML Learning
Xanadu / PennyLane Team
5 courses · 27 tutorials
Xanadu / PennyLane Team
Xanadu
Xanadu / Community
Xanadu / QOSF Community
AWS Quantum Technologies team
Implement a patch quantum GAN in PennyLane with a parametric quantum generator and classical neural network discriminator. Covers adversarial training, mode collapse, and how entanglement contributes to output diversity.
Reduce molecular simulation cost by selecting active orbitals in PennyLane. Combine active space selection with VQE for accurate molecular ground state energies.
Cut noise on NISQ devices with PennyLane: implement zero-noise extrapolation and probabilistic error cancellation, with a working example that beats the unmitigated baseline.
Train variational quantum circuits directly on realistic noise models using PennyLane. Compare circuits trained with and without noise, insert depolarizing and amplitude damping channels, and apply noise injection techniques to improve real hardware performance.
Implement a simplified ADAPT-VQE algorithm in PennyLane. Build an operator pool, greedily select operators by gradient magnitude, grow the ansatz iteratively, and compare convergence against fixed UCCSD for the H2 molecule.
Build a complete hybrid quantum-classical optimization pipeline: PennyLane QNode wrapped as a PyTorch layer, automatic differentiation through quantum circuits, Adam optimizer training on a binary classification task, and comparison to classical logistic regression.
Implement the Quantum Approximate Optimisation Algorithm to solve the MaxCut graph problem using PennyLane, and understand how QAOA bridges quantum computing and combinatorial optimisation.
Use PennyLane's shot-adaptive optimizer to allocate measurement shots intelligently across circuit parameters.
Run your first differentiable quantum circuit in PennyLane. Build a Bell state, compute gradients, and see why PennyLane is the go-to framework for quantum ML.
Combine a classical pre-trained CNN with a parameterized quantum circuit for image classification using PennyLane's quantum transfer learning technique.
Understand why Clifford+T is the universal fault-tolerant gate set, the cost of T gates in magic state distillation, and how to analyze T-count with PennyLane.
Implement quantum natural gradient descent in PennyLane using the quantum Fisher information matrix. Compare convergence against standard gradient descent on a VQE benchmark.
Build a quantum classifier using PennyLane's parameterized circuits and train it to classify a simple dataset using gradient descent.
A conceptual and practical introduction to quantum machine learning: what QML is, data encoding strategies, parameterized quantum circuits, and a complete classification example.
Optimize variational circuits using finite shots in PennyLane. Compare parameter-shift, SPSA, and natural gradient estimators for shot-limited hardware settings.
Learn how to build quantum kernel functions with PennyLane, use them with scikit-learn's SVM, and understand when quantum kernels might offer an advantage over classical kernels, with a full working classification example.
Implement the Variational Quantum Eigensolver to find the ground state energy of a hydrogen molecule using PennyLane and gradient-based optimization.
Understand why barren plateaus occur in deep variational circuits, how to detect them in PennyLane, and practical strategies to avoid them including layerwise training and structured ansatze.
Full VQE for LiH using PennyLane's qchem module: molecular Hamiltonian, Hartree-Fock initial state, UCCSD ansatz, optimization, and potential energy surface scan.
Build a complete binary quantum classifier with angle encoding, strongly entangling layers, BCE loss, and Adam optimizer, trained on the moons dataset, with decision boundary visualization and comparison to logistic regression.
Walk through a real VQE simulation in PennyLane: build the H2 Hamiltonian, construct a UCCSD ansatz, and converge to the ground state energy in under 50 iterations.
Explore PennyLane's Lightning family of high-performance simulation backends, learn how to use adjoint differentiation for efficient gradient computation, and understand when to deploy lightning.qubit, lightning.gpu, and lightning.kokkos.
Implement quantum teleportation in PennyLane: creating the entangled pair, Bell measurement, classical correction, and verifying the teleported state.
Run QAOA on Max-Cut in PennyLane end to end: encode the graph as a cost Hamiltonian, parameterize the variational circuit, and optimize toward the maximum partition.
Build a quantum generative adversarial network in PennyLane with a quantum generator and classical discriminator.
Connect PennyLane to Amazon Braket backends to run hybrid quantum-classical workflows, from local simulation to IonQ trapped-ion hardware.
Use PennyLane Catalyst to JIT-compile hybrid quantum-classical programs with JAX, enabling fast execution on both simulators and quantum hardware.