NeuralNetworkClassifier

class NeuralNetworkClassifier(neural_network, loss='squared_error', one_hot=False, optimizer=None, warm_start=False, initial_point=None, callback=None)

Bases: TrainableModel, ClassifierMixin

Implements a basic quantum neural network classifier. Implements Scikit-Learn compatible methods for classification and extends ClassifierMixin. See Scikit-Learn for more details.

Parameters:

• neural_network (NeuralNetwork) – An instance of an quantum neural network. If the neural network has a one-dimensional output, i.e., neural_network.output_shape=(1,), then it is expected to return values in [-1, +1] and it can only be used for binary classification. If the output is multi-dimensional, it is assumed that the result is a probability distribution, i.e., that the entries are non-negative and sum up to one. Then there are two options, either one-hot encoding or not. In case of one-hot encoding, each probability vector resulting a neural network is considered as one sample and the loss function is applied to the whole vector. Otherwise, each entry of the probability vector is considered as an individual sample and the loss function is applied to the index and weighted with the corresponding probability.

• loss (str | Loss) – A target loss function to be used in training. Default is squared_error, i.e. L2 loss. Can be given either as a string for ‘absolute_error’ (i.e. L1 Loss), ‘squared_error’, ‘cross_entropy’, or as a loss function implementing the Loss interface.

• one_hot (bool) – Determines in the case of a multi-dimensional result of the neural_network how to interpret the result. If True it is interpreted as a single one-hot-encoded sample (e.g. for ‘CrossEntropy’ loss function), and if False as a set of individual predictions with occurrence probabilities (the index would be the prediction and the value the corresponding frequency, e.g. for absolute/squared loss). In case of a one-dimensional categorical output, this option determines how to encode the target data (i.e. one-hot or integer encoding).

• optimizer (Optimizer | Minimizer | None) – An instance of an optimizer or a callable to be used in training. Refer to Minimizer for more information on the callable protocol. When None defaults to SLSQP.

• warm_start (bool) – Use weights from previous fit to start next fit.

• initial_point (np.ndarray) – Initial point for the optimizer to start from.

• callback (Callable[[np.ndarray, float], None] | None) – a reference to a user’s callback function that has two parameters and returns None. The callback can access intermediate data during training. On each iteration an optimizer invokes the callback and passes current weights as an array and a computed value as a float of the objective function being optimized. This allows to track how well optimization / training process is going on.

Raises:

QiskitMachineLearningError – unknown loss, invalid neural network

Attributes

callback

Return the callback.

fit_result

Returns a resulting object from the optimization procedure. Please refer to the documentation of the OptimizerResult class for more details.

Raises:

QiskitMachineLearningError – If the model has not been fit.

initial_point

Returns current initial point

loss

Returns the underlying neural network.

neural_network

Returns the underlying neural network.

num_classes

The number of classes found in the most recent fit.

If called before fit(), this will return None.

optimizer

Returns an optimizer to be used in training.

warm_start

Returns the warm start flag.

weights

Returns trained weights as a numpy array. The weights can be also queried by calling model.fit_result.x, but in this case their representation depends on the optimizer used.

Raises:

QiskitMachineLearningError – If the model has not been fit.

Methods

fit(X, y)

Fit the model to data matrix X and target(s) y.

Parameters:

• X (ndarray) – The input data.

• y (ndarray) – The target values.

Returns:

returns a trained model.

Return type:

self

Raises:

QiskitMachineLearningError – In case of invalid data (e.g. incompatible with network)

classmethod load(file_name)

Loads a model from the file. If the loaded model is not an instance of the class whose method was called, then a warning is raised. Nevertheless, the loaded model may be a valid model.

Parameters:

file_name (str) – a file name or path to load a model from.

Returns:

A loaded model.

Raises:

TypeError – if a loaded model is not an instance of the expected class.

Return type:

Any

predict(X)

Perform classification on samples in X.

Parameters:

X (np.ndarray) – Input features. For a callable kernel (an instance of BaseKernel), the shape should be (m_samples, n_features). For a pre-computed kernel, the shape should be (m_samples, n_samples). Here, m_* denotes the set to be predicted, and n_* denotes the size of the training set. In the case of a pre-computed kernel, the kernel values in X must be calculated with respect to the elements of the set to be predicted and the training set.

Returns:

An array of shape (n_samples,), representing the predicted class labels for

each sample in X.

Return type:

np.ndarray

Raises:

• QiskitMachineLearningError –

  • If the predict() method is called before the model has been fit.

• ValueError –

  • If the pre-computed kernel matrix has the wrong shape and/or dimension.

predict_proba(X)

Extracts the predicted probabilities for each class based on the output of a neural network.

Parameters:

X (np.ndarray) – Input features. For a callable kernel (an instance of BaseKernel), the shape should be (m_samples, n_features). For a pre-computed kernel, the shape should be (m_samples, n_samples). Here, m_* denotes the set to be predicted, and n_* denotes the size of the training set. In the case of a pre-computed kernel, the kernel values in X must be calculated with respect to the elements of the set to be predicted and the training set.

Returns:

An array of shape (n_samples, n_classes) representing the predicted class

probabilities (in the range \([0, 1]\)) for each sample in X.

Return type:

np.ndarray

save(file_name)

Saves this model to the specified file. Internally, the model is serialized via dill. All parameters are saved, including a primitive instance that is referenced by internal objects. That means if a model is loaded from a file and is used, for instance, for inference, the same primitive will be used even if a cloud primitive was used.

Parameters:

file_name (str) – a file name or path where to save the model.

score(X, y, sample_weight=None)

Returns a score of this model given samples and true values for the samples. In case of classification this should be mean accuracy, in case of regression the coefficient of determination \(R^2\) of the prediction.

Parameters:

• X (ndarray) – Test samples.

• y (ndarray) – True values for X.

• sample_weight (ndarray | None) – Sample weights. Default is None.

Returns:

a float score of the model.

Return type:

float