Quantum neural networks (qiskit_machine_learning.neural_networks)

A neural network is a parametrized network which may be defined as a artificial neural network - classical neural network - or as parametrized quantum circuits - quantum neural network. Furthermore, neural networks can be defined with respect to a discriminative or generative task.

Neural networks may be used, for example, with the VQC algorithm.

See also the TorchConnector that allows the use of these neural networks in code written to PyTorch.

Neural Network Base Classes

NeuralNetwork	Abstract Neural Network class providing forward and backward pass and handling batched inputs.
SamplingNeuralNetwork	A sampling neural network abstract class for all (quantum) neural networks within Qiskit's machine learning module that generate samples instead of (expected) values.

Neural Networks

OpflowQNN	Pending deprecation: Opflow Quantum Neural Network.
TwoLayerQNN	Pending deprecation: Two Layer Quantum Neural Network consisting of a feature map, a ansatz, and an observable.
CircuitQNN	Pending deprecation: A sampling neural network based on a given quantum circuit.
EstimatorQNN	A neural network implementation based on the Estimator primitive.
SamplerQNN	A neural network implementation based on the Sampler primitive.

Neural Network Metrics

EffectiveDimension	This class computes the global effective dimension for a Qiskit NeuralNetwork following the definition used in [1].
LocalEffectiveDimension	This class computes the local effective dimension for a Qiskit NeuralNetwork following the definition used in [1].