# Qiskit Machine Learning
[](https://opensource.org/licenses/Apache-2.0)
Qiskit Machine Learning introduces fundamental computational building blocks - such as Quantum Kernels
and Quantum Neural Networks - used in different applications, including classification and regression.
On the one hand, this design is very easy to use and allows users to rapidly prototype a first model
without deep quantum computing knowledge. On the other hand, Qiskit Machine Learning is very flexible,
and users can easily extend it to support cutting-edge quantum machine learning research.
Qiskit Machine Learning provides the
[FidelityQuantumKernel](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.kernels.QuantumKernel.html#qiskit_machine_learning.kernels.FidelityQuantumKernel)
class that makes use of the [Fidelity](https://qiskit-community.github.io/qiskit-algorithms/stubs/qiskit_algorithms.state_fidelities.BaseStateFidelity.html) algorithm introduced in Qiskit Algorithms and can be easily used
to directly compute kernel matrices for given datasets or can be passed to a Quantum Support Vector Classifier
[QSVC](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.algorithms.QSVC.html#qiskit_machine_learning.algorithms.QSVC) or
Quantum Support Vector Regressor
[QSVR](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.algorithms.QSVR.html#qiskit_machine_learning.algorithms.QSVR)
to quickly start solving classification or regression problems.
It also can be used with many other existing kernel-based machine learning algorithms from established
classical frameworks.
Qiskit Machine Learning defines a generic interface for neural networks that is implemented by different
quantum neural networks. Two core implementations are readily provided, such as the
[EstimatorQNN](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.neural_networks.EstimatorQNN.html),
and the [SamplerQNN](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.neural_networks.SamplerQNN.html).
The [EstimatorQNN](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.neural_networks.EstimatorQNN.html)
leverages the [Estimator](https://docs.quantum.ibm.com/api/qiskit/qiskit.primitives.BaseEstimator) primitive from Qiskit and
allows users to combine parametrized quantum circuits with quantum mechanical observables. The circuits can be constructed using, for example, building blocks
from Qiskit’s circuit library, and the QNN’s output is given by the expected value of the observable.
The [SamplerQNN](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.neural_networks.SamplerQNN.html)
leverages another primitive introduced in Qiskit, the [Sampler](https://docs.quantum.ibm.com/api/qiskit/qiskit.primitives.BaseSampler) primitive.
This neural network translates quasi-probabilities of bitstrings estimated by the primitive into a desired output. This
translation step can be used to interpret a given bitstring in a particular context, e.g. translating it into a set of classes.
The neural networks include the functionality to evaluate them for a given input as well as to compute the
corresponding gradients, which is important for efficient training. To train and use neural networks,
Qiskit Machine Learning provides a variety of learning algorithms such as the
[NeuralNetworkClassifier](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.algorithms.NeuralNetworkClassifier.html#qiskit_machine_learning.algorithms.NeuralNetworkClassifier)
and
[NeuralNetworkRegressor](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.algorithms.NeuralNetworkRegressor.html#qiskit_machine_learning.algorithms.NeuralNetworkRegressor).
Both take a QNN as input and then use it in a classification or regression context.
To allow an easy start, two convenience implementations are provided - the Variational Quantum Classifier
[VQC](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.algorithms.VQC.html#qiskit_machine_learning.algorithms.VQC)
as well as the Variational Quantum Regressor
[VQR](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.algorithms.VQR.html#qiskit_machine_learning.algorithms.VQR).
Both take just a feature map and an ansatz and construct the underlying QNN automatically.
In addition to the models provided directly in Qiskit Machine Learning, it has the
[TorchConnector](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.connectors.TorchConnector.html#qiskit_machine_learning.connectors.TorchConnector),
which allows users to integrate all of our quantum neural networks directly into the
[PyTorch](https://pytorch.org)
open source machine learning library. Thanks to Qiskit’s gradient algorithms, this includes automatic
differentiation - the overall gradients computed by [PyTorch](https://pytorch.org)
during the backpropagation take into
account quantum neural networks, too. The flexible design also allows the building of connectors
to other packages in the future.
## Installation
We encourage installing Qiskit Machine Learning via the pip tool (a python package manager).
```bash
pip install qiskit-machine-learning
```
**pip** will handle all dependencies automatically and you will always install the latest
(and well-tested) version.
If you want to work on the very latest work-in-progress versions, either to try features ahead of
their official release or if you want to contribute to Machine Learning, then you can install from source.
To do this follow the instructions in the
[documentation](https://qiskit-community.github.io/qiskit-machine-learning/getting_started.html#installation).
----------------------------------------------------------------------------------------------------
### Optional Installs
* **PyTorch**, may be installed either using command `pip install 'qiskit-machine-learning[torch]'` to install the
package or refer to PyTorch [getting started](https://pytorch.org/get-started/locally/). When PyTorch
is installed, the `TorchConnector` facilitates its use of quantum computed networks.
* **Sparse**, may be installed using command `pip install 'qiskit-machine-learning[sparse]'` to install the
package. Sparse being installed will enable the usage of sparse arrays/tensors.
### Creating Your First Machine Learning Programming Experiment in Qiskit
Now that Qiskit Machine Learning is installed, it's time to begin working with the Machine Learning module.
Let's try an experiment using VQC (Variational Quantum Classifier) algorithm to
train and test samples from a data set to see how accurately the test set can
be classified.
```python
from qiskit.circuit.library import TwoLocal, ZZFeatureMap
from qiskit_algorithms.optimizers import COBYLA
from qiskit_algorithms.utils import algorithm_globals
from qiskit_machine_learning.algorithms import VQC
from qiskit_machine_learning.datasets import ad_hoc_data
seed = 1376
algorithm_globals.random_seed = seed
# Use ad hoc data set for training and test data
feature_dim = 2 # dimension of each data point
training_size = 20
test_size = 10
# training features, training labels, test features, test labels as np.ndarray,
# one hot encoding for labels
training_features, training_labels, test_features, test_labels = ad_hoc_data(
training_size=training_size, test_size=test_size, n=feature_dim, gap=0.3
)
feature_map = ZZFeatureMap(feature_dimension=feature_dim, reps=2, entanglement="linear")
ansatz = TwoLocal(feature_map.num_qubits, ["ry", "rz"], "cz", reps=3)
vqc = VQC(
feature_map=feature_map,
ansatz=ansatz,
optimizer=COBYLA(maxiter=100),
)
vqc.fit(training_features, training_labels)
score = vqc.score(test_features, test_labels)
print(f"Testing accuracy: {score:0.2f}")
```
### Further examples
Learning path notebooks may be found in the
[Machine Learning tutorials](https://qiskit-community.github.io/qiskit-machine-learning/tutorials/index.html) section
of the documentation and are a great place to start.
Another good place to learn the fundamentals of quantum machine learning is the
[Quantum Machine Learning](https://github.com/Qiskit/textbook/tree/main/notebooks/quantum-machine-learning#) notebooks from the original Qiskit Textbook. The notebooks are convenient for beginners who are eager to learn
quantum machine learning from scratch, as well as understand the background and theory behind algorithms in
Qiskit Machine Learning. The notebooks cover a variety of topics to build understanding of parameterized
circuits, data encoding, variational algorithms etc., and in the end the ultimate goal of machine
learning - how to build and train quantum ML models for supervised and unsupervised learning.
The Textbook notebooks are complementary to the tutorials of this module; whereas these tutorials focus
on actual Qiskit Machine Learning algorithms, the Textbook notebooks more explain and detail underlying fundamentals
of quantum machine learning.
----------------------------------------------------------------------------------------------------
## Contribution Guidelines
If you'd like to contribute to Qiskit, please take a look at our
[contribution guidelines](https://github.com/qiskit-community/qiskit-machine-learning/blob/main/CONTRIBUTING.md).
This project adheres to Qiskit's [code of conduct](https://github.com/qiskit-community/qiskit-machine-learning/blob/main/CODE_OF_CONDUCT.md).
By participating, you are expected to uphold this code.
We use [GitHub issues](https://github.com/qiskit-community/qiskit-machine-learning/issues) for tracking requests and bugs. Please
[join the Qiskit Slack community](https://qisk.it/join-slack)
and for discussion and simple questions.
For questions that are more suited for a forum, we use the **Qiskit** tag in [Stack Overflow](https://stackoverflow.com/questions/tagged/qiskit).
## Authors and Citation
Machine Learning was inspired, authored and brought about by the collective work of a team of researchers.
Machine Learning continues to grow with the help and work of
[many people](https://github.com/qiskit-community/qiskit-machine-learning/graphs/contributors), who contribute
to the project at different levels.
If you use Qiskit, please cite as per the provided
[BibTeX file](https://github.com/Qiskit/qiskit/blob/main/CITATION.bib).
## License
This project uses the [Apache License 2.0](https://github.com/qiskit-community/qiskit-machine-learning/blob/main/LICENSE.txt).
Raw data
{
"_id": null,
"home_page": "https://github.com/qiskit-community/qiskit-machine-learning",
"name": "qiskit-machine-learning",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "",
"keywords": "qiskit sdk quantum machine learning ml",
"author": "Qiskit Machine Learning Development Team",
"author_email": "qiskit@us.ibm.com",
"download_url": "https://files.pythonhosted.org/packages/32/be/1a340139239fd2ebebc70c545698a6830a702098f12e07791e94ea5d3820/qiskit-machine-learning-0.7.2.tar.gz",
"platform": null,
"description": "# Qiskit Machine Learning\n\n[](https://opensource.org/licenses/Apache-2.0)\n\nQiskit Machine Learning introduces fundamental computational building blocks - such as Quantum Kernels\nand Quantum Neural Networks - used in different applications, including classification and regression.\nOn the one hand, this design is very easy to use and allows users to rapidly prototype a first model\nwithout deep quantum computing knowledge. On the other hand, Qiskit Machine Learning is very flexible,\nand users can easily extend it to support cutting-edge quantum machine learning research.\n\nQiskit Machine Learning provides the\n[FidelityQuantumKernel](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.kernels.QuantumKernel.html#qiskit_machine_learning.kernels.FidelityQuantumKernel)\nclass that makes use of the [Fidelity](https://qiskit-community.github.io/qiskit-algorithms/stubs/qiskit_algorithms.state_fidelities.BaseStateFidelity.html) algorithm introduced in Qiskit Algorithms and can be easily used\nto directly compute kernel matrices for given datasets or can be passed to a Quantum Support Vector Classifier \n[QSVC](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.algorithms.QSVC.html#qiskit_machine_learning.algorithms.QSVC) or\nQuantum Support Vector Regressor\n[QSVR](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.algorithms.QSVR.html#qiskit_machine_learning.algorithms.QSVR)\nto quickly start solving classification or regression problems.\nIt also can be used with many other existing kernel-based machine learning algorithms from established\nclassical frameworks.\n\nQiskit Machine Learning defines a generic interface for neural networks that is implemented by different\nquantum neural networks. Two core implementations are readily provided, such as the\n[EstimatorQNN](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.neural_networks.EstimatorQNN.html),\nand the [SamplerQNN](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.neural_networks.SamplerQNN.html).\nThe [EstimatorQNN](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.neural_networks.EstimatorQNN.html)\nleverages the [Estimator](https://docs.quantum.ibm.com/api/qiskit/qiskit.primitives.BaseEstimator) primitive from Qiskit and \nallows users to combine parametrized quantum circuits with quantum mechanical observables. The circuits can be constructed using, for example, building blocks\nfrom Qiskit\u2019s circuit library, and the QNN\u2019s output is given by the expected value of the observable.\nThe [SamplerQNN](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.neural_networks.SamplerQNN.html)\nleverages another primitive introduced in Qiskit, the [Sampler](https://docs.quantum.ibm.com/api/qiskit/qiskit.primitives.BaseSampler) primitive. \nThis neural network translates quasi-probabilities of bitstrings estimated by the primitive into a desired output. This \ntranslation step can be used to interpret a given bitstring in a particular context, e.g. translating it into a set of classes.\n\nThe neural networks include the functionality to evaluate them for a given input as well as to compute the\ncorresponding gradients, which is important for efficient training. To train and use neural networks,\nQiskit Machine Learning provides a variety of learning algorithms such as the\n[NeuralNetworkClassifier](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.algorithms.NeuralNetworkClassifier.html#qiskit_machine_learning.algorithms.NeuralNetworkClassifier)\nand\n[NeuralNetworkRegressor](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.algorithms.NeuralNetworkRegressor.html#qiskit_machine_learning.algorithms.NeuralNetworkRegressor).\nBoth take a QNN as input and then use it in a classification or regression context.\nTo allow an easy start, two convenience implementations are provided - the Variational Quantum Classifier\n[VQC](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.algorithms.VQC.html#qiskit_machine_learning.algorithms.VQC)\nas well as the Variational Quantum Regressor\n[VQR](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.algorithms.VQR.html#qiskit_machine_learning.algorithms.VQR).\nBoth take just a feature map and an ansatz and construct the underlying QNN automatically.\n\nIn addition to the models provided directly in Qiskit Machine Learning, it has the\n[TorchConnector](https://qiskit-community.github.io/qiskit-machine-learning/stubs/qiskit_machine_learning.connectors.TorchConnector.html#qiskit_machine_learning.connectors.TorchConnector),\nwhich allows users to integrate all of our quantum neural networks directly into the\n[PyTorch](https://pytorch.org)\nopen source machine learning library. Thanks to Qiskit\u2019s gradient algorithms, this includes automatic\ndifferentiation - the overall gradients computed by [PyTorch](https://pytorch.org)\nduring the backpropagation take into\naccount quantum neural networks, too. The flexible design also allows the building of connectors\nto other packages in the future.\n\n## Installation\n\nWe encourage installing Qiskit Machine Learning via the pip tool (a python package manager).\n\n```bash\npip install qiskit-machine-learning\n```\n\n**pip** will handle all dependencies automatically and you will always install the latest\n(and well-tested) version.\n\nIf you want to work on the very latest work-in-progress versions, either to try features ahead of\ntheir official release or if you want to contribute to Machine Learning, then you can install from source.\nTo do this follow the instructions in the\n [documentation](https://qiskit-community.github.io/qiskit-machine-learning/getting_started.html#installation).\n\n\n----------------------------------------------------------------------------------------------------\n\n### Optional Installs\n\n* **PyTorch**, may be installed either using command `pip install 'qiskit-machine-learning[torch]'` to install the\n package or refer to PyTorch [getting started](https://pytorch.org/get-started/locally/). When PyTorch\n is installed, the `TorchConnector` facilitates its use of quantum computed networks.\n\n* **Sparse**, may be installed using command `pip install 'qiskit-machine-learning[sparse]'` to install the\n package. Sparse being installed will enable the usage of sparse arrays/tensors.\n\n### Creating Your First Machine Learning Programming Experiment in Qiskit\n\nNow that Qiskit Machine Learning is installed, it's time to begin working with the Machine Learning module.\nLet's try an experiment using VQC (Variational Quantum Classifier) algorithm to\ntrain and test samples from a data set to see how accurately the test set can\nbe classified.\n\n```python\nfrom qiskit.circuit.library import TwoLocal, ZZFeatureMap\nfrom qiskit_algorithms.optimizers import COBYLA\nfrom qiskit_algorithms.utils import algorithm_globals\n\nfrom qiskit_machine_learning.algorithms import VQC\nfrom qiskit_machine_learning.datasets import ad_hoc_data\n\nseed = 1376\nalgorithm_globals.random_seed = seed\n\n# Use ad hoc data set for training and test data\nfeature_dim = 2 # dimension of each data point\ntraining_size = 20\ntest_size = 10\n\n# training features, training labels, test features, test labels as np.ndarray,\n# one hot encoding for labels\ntraining_features, training_labels, test_features, test_labels = ad_hoc_data(\n training_size=training_size, test_size=test_size, n=feature_dim, gap=0.3\n)\n\nfeature_map = ZZFeatureMap(feature_dimension=feature_dim, reps=2, entanglement=\"linear\")\nansatz = TwoLocal(feature_map.num_qubits, [\"ry\", \"rz\"], \"cz\", reps=3)\nvqc = VQC(\n feature_map=feature_map,\n ansatz=ansatz,\n optimizer=COBYLA(maxiter=100),\n)\nvqc.fit(training_features, training_labels)\n\nscore = vqc.score(test_features, test_labels)\nprint(f\"Testing accuracy: {score:0.2f}\")\n```\n\n### Further examples\n\nLearning path notebooks may be found in the\n[Machine Learning tutorials](https://qiskit-community.github.io/qiskit-machine-learning/tutorials/index.html) section\nof the documentation and are a great place to start. \n\nAnother good place to learn the fundamentals of quantum machine learning is the\n[Quantum Machine Learning](https://github.com/Qiskit/textbook/tree/main/notebooks/quantum-machine-learning#) notebooks from the original Qiskit Textbook. The notebooks are convenient for beginners who are eager to learn \nquantum machine learning from scratch, as well as understand the background and theory behind algorithms in\nQiskit Machine Learning. The notebooks cover a variety of topics to build understanding of parameterized\ncircuits, data encoding, variational algorithms etc., and in the end the ultimate goal of machine\nlearning - how to build and train quantum ML models for supervised and unsupervised learning. \nThe Textbook notebooks are complementary to the tutorials of this module; whereas these tutorials focus\non actual Qiskit Machine Learning algorithms, the Textbook notebooks more explain and detail underlying fundamentals\nof quantum machine learning.\n\n----------------------------------------------------------------------------------------------------\n\n## Contribution Guidelines\n\nIf you'd like to contribute to Qiskit, please take a look at our\n[contribution guidelines](https://github.com/qiskit-community/qiskit-machine-learning/blob/main/CONTRIBUTING.md).\nThis project adheres to Qiskit's [code of conduct](https://github.com/qiskit-community/qiskit-machine-learning/blob/main/CODE_OF_CONDUCT.md).\nBy participating, you are expected to uphold this code.\n\nWe use [GitHub issues](https://github.com/qiskit-community/qiskit-machine-learning/issues) for tracking requests and bugs. Please\n[join the Qiskit Slack community](https://qisk.it/join-slack)\nand for discussion and simple questions.\nFor questions that are more suited for a forum, we use the **Qiskit** tag in [Stack Overflow](https://stackoverflow.com/questions/tagged/qiskit).\n\n## Authors and Citation\n\nMachine Learning was inspired, authored and brought about by the collective work of a team of researchers.\nMachine Learning continues to grow with the help and work of\n[many people](https://github.com/qiskit-community/qiskit-machine-learning/graphs/contributors), who contribute\nto the project at different levels.\nIf you use Qiskit, please cite as per the provided\n[BibTeX file](https://github.com/Qiskit/qiskit/blob/main/CITATION.bib).\n\n## License\n\nThis project uses the [Apache License 2.0](https://github.com/qiskit-community/qiskit-machine-learning/blob/main/LICENSE.txt).\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Qiskit Machine Learning: A library of quantum computing machine learning experiments",
"version": "0.7.2",
"project_urls": {
"Bug Tracker": "https://github.com/qiskit-community/qiskit-machine-learning/issues",
"Documentation": "https://qiskit-community.github.io/qiskit-machine-learning/",
"Homepage": "https://github.com/qiskit-community/qiskit-machine-learning",
"Source Code": "https://github.com/qiskit-community/qiskit-machine-learning"
},
"split_keywords": [
"qiskit",
"sdk",
"quantum",
"machine",
"learning",
"ml"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "7f4aed252b41533f0fef82d0085339040277cdfba5c5ec7e816eefd92cf97b26",
"md5": "e44648f085bf3023e767df4cbe0fbec6",
"sha256": "e63c525e6fa5fd22e9005e3e09115c38c700823a6d693565d8811de206eed437"
},
"downloads": -1,
"filename": "qiskit_machine_learning-0.7.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e44648f085bf3023e767df4cbe0fbec6",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 97762,
"upload_time": "2024-02-29T16:41:36",
"upload_time_iso_8601": "2024-02-29T16:41:36.008063Z",
"url": "https://files.pythonhosted.org/packages/7f/4a/ed252b41533f0fef82d0085339040277cdfba5c5ec7e816eefd92cf97b26/qiskit_machine_learning-0.7.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "32be1a340139239fd2ebebc70c545698a6830a702098f12e07791e94ea5d3820",
"md5": "b3fb88e1d0301b259d133f56c8513cb6",
"sha256": "cd0a7cc562304ff74d4151d627d163a02d2f1d83e61e35b97e0a913141237964"
},
"downloads": -1,
"filename": "qiskit-machine-learning-0.7.2.tar.gz",
"has_sig": false,
"md5_digest": "b3fb88e1d0301b259d133f56c8513cb6",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 102930,
"upload_time": "2024-02-29T16:41:37",
"upload_time_iso_8601": "2024-02-29T16:41:37.414809Z",
"url": "https://files.pythonhosted.org/packages/32/be/1a340139239fd2ebebc70c545698a6830a702098f12e07791e94ea5d3820/qiskit-machine-learning-0.7.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-29 16:41:37",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "qiskit-community",
"github_project": "qiskit-machine-learning",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "qiskit",
"specs": [
[
">=",
"0.44"
]
]
},
{
"name": "qiskit-algorithms",
"specs": [
[
">=",
"0.2.0"
]
]
},
{
"name": "scipy",
"specs": [
[
">=",
"1.4"
]
]
},
{
"name": "numpy",
"specs": [
[
">=",
"1.17"
]
]
},
{
"name": "psutil",
"specs": [
[
">=",
"5"
]
]
},
{
"name": "scikit-learn",
"specs": [
[
">=",
"1.2.0"
]
]
},
{
"name": "fastdtw",
"specs": []
},
{
"name": "setuptools",
"specs": [
[
">=",
"40.1.0"
]
]
},
{
"name": "dill",
"specs": [
[
">=",
"0.3.4"
]
]
}
],
"tox": true,
"lcname": "qiskit-machine-learning"
}
JSON
