Notice: This library is no longer actively maintained. Its spiritual successor is PennyLane
The Quantum Machine Learning Toolbox (QMLT) is a Strawberry Fields application that simplifies the optimization of variational quantum circuits. Tasks for the QMLT range from variational eigensolvers and unitary learning to supervised and unsupervised machine learning with models based on a variational circuit.
The Quantum Machine Learning Toolbox supports:
- The training of user-provided variational circuits
- Automatic and numerical differentiation methods to compute gradients of circuit outputs
- Optimization, supervised and unsupervised learning tasks
- Regularization of circuit parameters
- Logging of training results
- Monitoring and visualization of training through matplotlib and TensorBoard
- Saving and restoring trained models
- Parallel computation/GPU usage for TensorFlow-based models
To get started, please see the online documentation.
Installation of the QMLT, as well as all required Python packages mentioned above, can be done using pip:
$ python -m pip install qmlt
To run all tests please run the following line from the main directory:
$ python -m unittest discover tests
Maria Schuld and Josh Izaac.
If you are doing research using Strawberry Fields, please cite our whitepaper and the QMLT documentation:
Nathan Killoran, Josh Izaac, Nicolás Quesada, Ville Bergholm, Matthew Amy, and Christian Weedbrook. Strawberry Fields: A Software Platform for Photonic Quantum Computing. arXiv, 2018. arXiv:1804.03159
Maria Schuld and Josh Izaac. Xanadu Quantum Machine Learning Toolbox documentation. https://qmlt.readthedocs.io.
- Source Code: https://github.com/XanaduAI/QMLT
- Issue Tracker: https://github.com/XanaduAI/QMLT/issues
If you are having issues, please let us know by posting the issue on our Github issue tracker.
We also have a Strawberry Fields Slack channel - come join the discussion and chat with our Strawberry Fields team.
QMLT is free and open source, released under the Apache License, Version 2.0.