API Reference

QML Regressors

`kernel.ml.QSVR`	Quantum Support Vector Regression
`kernel.ml.QKRR`	Quantum Kernel Ridge Regression.
`kernel.ml.QGPR`	Quantum Gaussian Process Regression (QGPR).
`qnn.QNNRegressor`	Quantum Neural Network for Regression.
`qrc.QRCRegressor`	Quantum Reservoir Computing for regression.

`kernel.ml.QSVC`	Quantum Support Vector Classification
`kernel.ml.QGPC`	Quantum Gaussian process classification (QGPC), that extends the scikit-learn sklearn.gaussian_process.GaussianProcessClassifier.
`qnn.QNNClassifier`	Quantum Neural Network for Classification.
`qrc.QRCClassifier`	Quantum Reservoir Computing for classification.

`encoding_circuit.YZ_CX_EncodingCircuit`	Creates the YZ-CX Encoding Circuit from reference [1].
`encoding_circuit.HighDimEncodingCircuit`	The high-dimensional encoding circuit from reference [1].
`encoding_circuit.HubregtsenEncodingCircuit`	Creates the data reuploading encoding circuit as presented in reference [1].
`encoding_circuit.ChebyshevTower`	A feature-map that is based on the Chebyshev Tower encoding.
`encoding_circuit.ChebyshevPQC`	Chebyshev Encoding Circuit from reference [1].
`encoding_circuit.MultiControlEncodingCircuit`	Encoding circuit with HZ encoding followed by controlled Rx, Ry Rz rotations.
`encoding_circuit.ChebyshevRx`	Simple Chebyshev encoding circuit build from Rx gates
`encoding_circuit.ParamZFeatureMap`	Parameterized Z feature map with optional CNOT gates between the default layers.
`encoding_circuit.KyriienkoEncodingCircuit`	Collection of encoding circuits introduced by Kyriienko et al. in reference [1].
`encoding_circuit.QiskitEncodingCircuit`	Wrapper to create sQUlearn encoding circuits from the Qiskit circuit library.
`encoding_circuit.QCNNEncodingCircuit`	Encoding circuit for quantum convolutional neural networks (QCNN).
`encoding_circuit.RandomLayeredEncodingCircuit`	Creates a random Layered encoding circuit with no trainable parameters.
`encoding_circuit.RandomEncodingCircuit`	Random parameterized encoding circuit with randomly picked gates, qubits and feature encodings.

`encoding_circuit.encoding_circuit_base.EncodingCircuitBase`	Encoding circuit base class
`encoding_circuit.PrunedEncodingCircuit`	Class for pruning redundant parameter of encoding circuits.
`encoding_circuit.LayeredEncodingCircuit`	A class for a simple creation of layered encoding circuits.
`encoding_circuit.EncodingCircuitDerivatives`	Class for automatic differentiation of encoding circuits.
`encoding_circuit.TranspiledEncodingCircuit`	Class for generated a Encoding Circuit with a transpiled circuit.

`encoding_circuit.automated_pruning`	Function for automated pruning of the parameters in the inputted parameterized quantum circuit.
`encoding_circuit.pruning_from_QFI`	Algorithm for determining the redundant parameters from the Quantum Fischer Information.

`observables.SinglePauli`	Observable constructed from a single Pauli operator of a single Qubit.
`observables.SummedPaulis`	Observable for summation of single Pauli operators.
`observables.SingleProbability`	Observable for measuring the probability of being in state 0 or 1 of a specified qubit.
`observables.SummedProbabilities`	Observable for summing single Qubit probabilities of binary states.
`observables.IsingHamiltonian`	Implementation of Ising type Hamiltonians.
`observables.CustomObservable`	Class for defining a custom observable.

`observables.observable_base.ObservableBase`	Base class for observables.
`observables.observable_derivatives.ObservableDerivatives`	Class for calculating derivatives of observables.

`Executor`	A class for executing quantum jobs on IBM Quantum systems or simulators.
`util.executor.ExecutorEstimator`	A class that creates an estimator primitive that wraps a Primitives instance.
`util.executor.ExecutorSampler`	A class that creates a sampler primitive that wraps a Primitives instance.

`kernel.matrix.FidelityKernel`	Fidelity Quantum Kernel.
`kernel.matrix.ProjectedQuantumKernel`	Projected Quantum Kernel for Quantum Kernel Algorithms

`kernel.loss.negative_log_likelihood.NLL`	Negative log likelihood loss function.
`kernel.loss.target_alignment.TargetAlignment`	Target alignment loss function.

QNN module for classification and regression.

`qnn.lowlevel_qnn.LowLevelQNN`	Low-level QNN factory, which creates the specific low-level QNN based on the quantum framework.
`qnn.lowlevel_qnn_qiskit.LowLevelQNNQiskit`	Low level implementation of QNNs and its derivatives based on Qiskit.
`qnn.lowlevel_qnn_qiskit.Expec`	Data structure that holds the set-up of derivative of the expectation value.
`qnn.lowlevel_qnn_pennylane.LowLevelQNNPennyLane`	Low level implementation of QNNs and its derivatives based on PennyLane.
`qnn.lowlevel_qnn_base.LowLevelQNNBase`	Base class for low-level QNNs.
`qnn.loss.SquaredLoss`	Squared loss for regression.
`qnn.loss.VarianceLoss`	Variance loss for regression.
`qnn.loss.ODELoss`	Squared loss for regression of Ordinary Differential Equations (ODEs).
`qnn.loss.ParameterRegularizationLoss`	Loss for parameter regularization.

Tools for training QNNs

`qnn.get_variance_fac`	Function for adjusting the variance regularization along the iterations.
`qnn.get_lr_decay`	Function for running an Adam optimization with a decay in the learning rate.
`qnn.ShotsFromRSTD`	Shot control for setting the shots of the gradient evaluation after the RSTD of the loss.
`qnn.training.train`	Function for training a given QNN.
`qnn.training.train_mini_batch`	Minimize a loss function using mini-batch gradient descent.

Module for optimizer implementations and wrappers.

`optimizers.Adam`	sQUlearn's implementation of the ADAM optimizer
`optimizers.LBFGSB`	Wrapper class for scipy's L-BFGS-B implementation.
`optimizers.SLSQP`	Wrapper class for scipy's SLSQP implementation.
`optimizers.SPSA`	Wrapper class for Qiskit's SPSA implementation.
`optimizers.SGLBO`	sQUlearn's implementation of the SGLBO optimizer

`util.OpTree`	Static class containing functions for working with OpTrees objects.
`util.optree.OpTreeList`	A OpTree node that represents its children as a list/array/vector.
`util.optree.OpTreeSum`	A OpTree node that sums over its children.
`util.optree.OpTreeCircuit`	A leaf of the OpTree that represents a circuit.
`util.optree.OpTreeOperator`	A leaf of the OpTree that represents an operator.
`util.optree.OpTreeExpectationValue`	Leaf of the OpTree that represents an expectation value of a circuit and an operator.
`util.optree.OpTreeMeasuredOperator`	Leaf of the OpTree that represents an measurement.
`util.optree.OpTreeContainer`	A container for arbitrary objects that can be used as leafs in the OpTree.
`util.optree.OpTreeValue`	A leaf that contains an evaluated value.

Class for converting a Qiskit circuit to a PennyLane circuit.

`observables.observable_base.ObservableBase`	Base class for observables.
`encoding_circuit.encoding_circuit_base.EncodingCircuitBase`	Encoding circuit base class
`kernel.matrix.kernel_matrix_base.KernelMatrixBase`	Base class for defining quantum kernels.
`kernel.loss.kernel_loss_base.KernelLossBase`	Empty parent class for a kernel loss function.
`optimizers.optimizer_base.OptimizerBase`	Base class for QNN optimizers.
`qnn.base_qnn.BaseQNN`	Base Class for Quantum Neural Networks.
`qnn.loss.LossBase`	Base class implementation for loss functions.
`qrc.base_qrc.BaseQRC`	Base class for Quantum Reservoir Computing (QRC) models.