Variational quantum classifier
Train compact PennyLane classifiers on synthetic binary datasets.
PennyLane quantum machine learning
Quantum Machine Learning
Modular research-grade workflows for variational classifiers, regressors, quantum kernels, QCNNs, autoencoders, metric learning, and deterministic benchmark comparisons.
Implemented workflows
Algorithms
Each workflow has a public Python API, command-line entry points where appropriate, and focused documentation generated from this repository.
Variational quantum regression
Fit continuous targets with a trainable quantum regressor.
Quantum convolutional neural network
Use shared quantum convolution blocks and pooling-style reductions.
Quantum autoencoder
Learn latent quantum representations and reconstruction maps.
Quantum kernel methods
Build quantum feature-map kernels for SVM workflows.
Quantum metric learning
Train embedding geometry with contrastive supervision.
Reference material
Documentation
Use the usage guide for API calls and CLI commands, results for deterministic reference outputs, theory notes for mathematical background, and the changelog for release history.
Install
Use the package from PyPI or source
The package is published as qml-pennylane and can also be installed from GitHub for development.