qiskit-community/qiskit-machine-learning

An open-source library built on Qiskit for quantum machine learning tasks at scale on quantum hardware and classical simulators

What it solves

Qiskit Machine Learning provides the fundamental building blocks needed to create and train machine learning models using quantum computers. It bridges the gap between quantum computing and classical machine learning by providing high-level tools for classification and regression tasks.

How it works

The library implements several core quantum machine learning approaches:

  • Kernel-based methods: Uses the FidelityQuantumKernel to compute kernel matrices, which can then be used with Quantum Support Vector Classifiers (QSVC) or Regressors (QSVR).
  • Quantum Neural Networks (QNNs): Provides a generic interface for neural networks via EstimatorQNN (which outputs expected values of observables) and SamplerQNN (which translates bit-string counts into outputs).
  • Variational Algorithms: High-level tools like the Variational Quantum Classifier (VQC) and Variational Quantum Regressor (VQR) automatically construct QNNs using feature maps and ansatze.
  • PyTorch Integration: The TorchConnector allows QNNs to be integrated into PyTorch workflows, enabling automatic differentiation and the creation of hybrid quantum-classical neural networks.

Who it’s for

It is designed for both beginners who want to prototype quantum ML models without deep quantum physics knowledge, and researchers conducting innovative proofs-of-concept in the field.

Highlights

  • Hybrid Workflows: Seamless integration with PyTorch for hybrid quantum-classical models.
  • User-friendly API: High-level syntax for quickly building VQC and VQR models.
  • ** uma a flexible framework**: Supports both kernel-based methods and neural network-based approaches.
  • Extensible Architecture: Built on the Qiskit SDK to allow for the integration of new cutting-edge features.

Related

  • Project
    qiskit-community/qiskit-nature

    An open-source framework for solving quantum mechanical natural science problems, such as molecular electronic structures and lattice models, using quantum computing algorithms.

  • Project
    mit-han-lab/torchquantum

    A PyTorch-based framework for simulating quantum computations on classical hardware, enabling the training of parameterized quantum circuits and hybrid classical-quantum models.

  • Project
    atomistic-machine-learning/schnetpack

    A deep learning toolbox for predicting quantum-chemical properties of molecules and materials using atomistic neural networks.

  • Project
    softwareQinc/qpp

    A modern C++ general-purpose quantum computing library for simulating arbitrary quantum processes with high performance and low dependencies.

  • Project
    tensorflow/quantum

    TensorFlow Quantum is a Python library that integrates Cirq quantum circuits with TensorFlow/Keras, providing high‑performance hybrid quantum‑classical machine‑learning models, automatic differentiation, and scalable simulation via qsim.