English
Languages
English
Bengali
French
Hindi
Italian
Japanese
Korean
Malayalam
Russian
Spanish
Tamil
Turkish
Vietnamese
Shortcuts

Neural Network Classifier & Regressor

In this tutorial we show how the NeuralNetworkClassifier and NeuralNetworkRegressor are used. Both take as an input a (Quantum) NeuralNetwork and leverage it in a specific context. In both cases we also provide a pre-configured variant for convenience, the Variational Quantum Classifier (VQC) and Variational Quantum Regressor (VQR). The tutorial is structured as follows:

  1. Classification

    • Classification with an OpflowQNN

    • Classification with a CircuitQNN

    • Variational Quantum Classifier (VQC)

  2. Regression

    • Regression with an OpflowQNN

    • Variational Quantum Regressor (VQR)

[1]:
import numpy as np
import matplotlib.pyplot as plt

from qiskit import Aer, QuantumCircuit
from qiskit.opflow import Z, I, StateFn
from qiskit.utils import QuantumInstance
from qiskit.circuit import Parameter
from qiskit.circuit.library import RealAmplitudes, ZZFeatureMap
from qiskit.algorithms.optimizers import COBYLA, L_BFGS_B

from qiskit_machine_learning.neural_networks import TwoLayerQNN, CircuitQNN
from qiskit_machine_learning.algorithms.classifiers import NeuralNetworkClassifier, VQC
from qiskit_machine_learning.algorithms.regressors import NeuralNetworkRegressor, VQR

from typing import Union

from qiskit_machine_learning.exceptions import QiskitMachineLearningError

from IPython.display import clear_output
[2]:
quantum_instance = QuantumInstance(Aer.get_backend('aer_simulator'), shots=1024)

Classification

We prepare a simple classification dataset to illustrate the following algorithms.

[3]:
num_inputs = 2
num_samples = 20
X = 2*np.random.rand(num_samples, num_inputs) - 1
y01 = 1*(np.sum(X, axis=1) >= 0)  # in { 0,  1}
y = 2*y01-1                       # in {-1, +1}
y_one_hot = np.zeros((num_samples, 2))
for i in range(num_samples):
    y_one_hot[i, y01[i]] = 1

for x, y_target in zip(X, y):
    if y_target == 1:
        plt.plot(x[0], x[1], 'bo')
    else:
        plt.plot(x[0], x[1], 'go')
plt.plot([-1, 1], [1, -1], '--', color='black')
plt.show()
../_images/tutorials_02_neural_network_classifier_and_regressor_4_0.png

Classification with the an OpflowQNN

First we show how an OpflowQNN can be used for classification within a NeuralNetworkClassifier. In this context, the OpflowQNN is expected to return one-dimensional output in \([-1, +1]\). This only works for binary classification and we assign the two classes to \(\{-1, +1\}\). For convenience, we use the TwoLayerQNN, which is a special type of OpflowQNN defined via a feature map and an ansatz.

[4]:
# construct QNN
opflow_qnn = TwoLayerQNN(num_inputs, quantum_instance=quantum_instance)
[5]:
# QNN maps inputs to [-1, +1]
opflow_qnn.forward(X[0, :], np.random.rand(opflow_qnn.num_weights))
[5]:
array([[-0.84179687]])

We will add a callback function called callback_graph. This will be called for each iteration of the optimizer and will be passed two parameters: the current weights and the value of the objective function at those weights. For our function, we append the value of the objective function to an array so we can plot iteration versus objective function value and update the graph with each iteration. However, you can do whatever you want with a callback function as long as it gets the two parameters mentioned passed.

[6]:
# callback function that draws a live plot when the .fit() method is called
def callback_graph(weights, obj_func_eval):
    clear_output(wait=True)
    objective_func_vals.append(obj_func_eval)
    plt.title("Objective function value against iteration")
    plt.xlabel("Iteration")
    plt.ylabel("Objective function value")
    plt.plot(range(len(objective_func_vals)), objective_func_vals)
    plt.show()
[7]:
# construct neural network classifier
opflow_classifier = NeuralNetworkClassifier(opflow_qnn, optimizer=COBYLA(), callback=callback_graph)
[8]:
# create empty array for callback to store evaluations of the objective function
objective_func_vals = []
plt.rcParams["figure.figsize"] = (12, 6)

# fit classifier to data
opflow_classifier.fit(X, y)

# return to default figsize
plt.rcParams["figure.figsize"] = (6, 4)

# score classifier
opflow_classifier.score(X, y)
../_images/tutorials_02_neural_network_classifier_and_regressor_11_0.png
[8]:
0.85
[9]:
# evaluate data points
y_predict = opflow_classifier.predict(X)

# plot results
# red == wrongly classified
for x, y_target, y_p in zip(X, y, y_predict):
    if y_target == 1:
        plt.plot(x[0], x[1], 'bo')
    else:
        plt.plot(x[0], x[1], 'go')
    if y_target != y_p:
        plt.scatter(x[0], x[1], s=200, facecolors='none', edgecolors='r', linewidths=2)
plt.plot([-1, 1], [1, -1], '--', color='black')
plt.show()
../_images/tutorials_02_neural_network_classifier_and_regressor_12_0.png

Classification with a CircuitQNN

Next we show how a CircuitQNN can be used for classification within a NeuralNetworkClassifier. In this context, the CircuitQNN is expected to return \(d\)-dimensional probability vector as output, where \(d\) denotes the number of classes. Sampling from a QuantumCircuit automatically results in a probability distribution and we just need to define a mapping from the measured bitstrings to the different classes. For binary classification we use the parity mapping.

[10]:
# construct feature map
feature_map = ZZFeatureMap(num_inputs)

# construct ansatz
ansatz = RealAmplitudes(num_inputs, reps=1)

# construct quantum circuit
qc = QuantumCircuit(num_inputs)
qc.append(feature_map, range(num_inputs))
qc.append(ansatz, range(num_inputs))
qc.decompose().draw(output='mpl')
[10]:
../_images/tutorials_02_neural_network_classifier_and_regressor_14_0.png
[11]:
# parity maps bitstrings to 0 or 1
def parity(x):
    return '{:b}'.format(x).count('1') % 2
output_shape = 2  # corresponds to the number of classes, possible outcomes of the (parity) mapping.
[12]:
# construct QNN
circuit_qnn = CircuitQNN(circuit=qc,
                         input_params=feature_map.parameters,
                         weight_params=ansatz.parameters,
                         interpret=parity,
                         output_shape=output_shape,
                         quantum_instance=quantum_instance)
[13]:
# construct classifier
circuit_classifier = NeuralNetworkClassifier(neural_network=circuit_qnn,
                                             optimizer=COBYLA(),
                                             callback=callback_graph)
[14]:
# create empty array for callback to store evaluations of the objective function
objective_func_vals = []
plt.rcParams["figure.figsize"] = (12, 6)

# fit classifier to data
circuit_classifier.fit(X, y01)

# return to default figsize
plt.rcParams["figure.figsize"] = (6, 4)

# score classifier
circuit_classifier.score(X, y01)
../_images/tutorials_02_neural_network_classifier_and_regressor_18_0.png
[14]:
0.8
[15]:
# evaluate data points
y_predict = circuit_classifier.predict(X)

# plot results
# red == wrongly classified
for x, y_target, y_p in zip(X, y01, y_predict):
    if y_target == 1:
        plt.plot(x[0], x[1], 'bo')
    else:
        plt.plot(x[0], x[1], 'go')
    if y_target != y_p:
        plt.scatter(x[0], x[1], s=200, facecolors='none', edgecolors='r', linewidths=2)
plt.plot([-1, 1], [1, -1], '--', color='black')
plt.show()
../_images/tutorials_02_neural_network_classifier_and_regressor_19_0.png

Variational Quantum Classifier (VQC)

The VQC is a special variant of the NeuralNetworkClassifier with a CircuitQNN. It applies a parity mapping (or extensions to multiple classes) to map from the bitstring to the classification, which results in a probability vector, which is interpreted as a one-hot encoded result. By default, it applies this the CrossEntropyLoss function that expects labels given in one-hot encoded format and will return predictions in that format too.

[16]:
# construct feature map, ansatz, and optimizer
feature_map = ZZFeatureMap(num_inputs)
ansatz = RealAmplitudes(num_inputs, reps=1)

# construct variational quantum classifier
vqc = VQC(feature_map=feature_map,
          ansatz=ansatz,
          loss='cross_entropy',
          optimizer=COBYLA(),
          quantum_instance=quantum_instance,
          callback=callback_graph)
[17]:
# create empty array for callback to store evaluations of the objective function
objective_func_vals = []
plt.rcParams["figure.figsize"] = (12, 6)

# fit classifier to data
vqc.fit(X, y_one_hot)

# return to default figsize
plt.rcParams["figure.figsize"] = (6, 4)

# score classifier
vqc.score(X, y_one_hot)
../_images/tutorials_02_neural_network_classifier_and_regressor_22_0.png
[17]:
0.8
[18]:
# evaluate data points
y_predict = vqc.predict(X)

# plot results
# red == wrongly classified
for x, y_target, y_p in zip(X, y_one_hot, y_predict):
    if y_target[0] == 1:
        plt.plot(x[0], x[1], 'bo')
    else:
        plt.plot(x[0], x[1], 'go')
    if not np.all(y_target == y_p):
        plt.scatter(x[0], x[1], s=200, facecolors='none', edgecolors='r', linewidths=2)
plt.plot([-1, 1], [1, -1], '--', color='black')
plt.show()
../_images/tutorials_02_neural_network_classifier_and_regressor_23_0.png

Regression

We prepare a simple regression dataset to illustrate the following algorithms.

[19]:
num_samples = 20
eps = 0.2
lb, ub = -np.pi, np.pi
X_ = np.linspace(lb, ub, num=50).reshape(50, 1)
f = lambda x: np.sin(x)

X = (ub - lb)*np.random.rand(num_samples, 1) + lb
y = f(X[:,0]) + eps*(2*np.random.rand(num_samples)-1)

plt.plot(X_, f(X_), 'r--')
plt.plot(X, y, 'bo')
plt.show()
../_images/tutorials_02_neural_network_classifier_and_regressor_25_0.png

Regression with an OpflowQNN

Here we restrict to regression with an OpflowQNN that returns values in \([-1, +1]\). More complex and also multi-dimensional models could be constructed, also based on CircuitQNN but that exceeds the scope of this tutorial.

[20]:
# construct simple feature map
param_x = Parameter('x')
feature_map = QuantumCircuit(1, name='fm')
feature_map.ry(param_x, 0)

# construct simple ansatz
param_y = Parameter('y')
ansatz = QuantumCircuit(1, name='vf')
ansatz.ry(param_y, 0)

# construct QNN
regression_opflow_qnn = TwoLayerQNN(1, feature_map, ansatz, quantum_instance=quantum_instance)
[21]:
# construct the regressor from the neural network
regressor = NeuralNetworkRegressor(neural_network=regression_opflow_qnn,
                                   loss='l2',
                                   optimizer=L_BFGS_B(),
                                   callback=callback_graph)
[22]:
# create empty array for callback to store evaluations of the objective function
objective_func_vals = []
plt.rcParams["figure.figsize"] = (12, 6)

# fit to data
regressor.fit(X, y)

# return to default figsize
plt.rcParams["figure.figsize"] = (6, 4)

# score the result
regressor.score(X, y)
../_images/tutorials_02_neural_network_classifier_and_regressor_29_0.png
[22]:
0.9703336921325691
[23]:
# plot target function
plt.plot(X_, f(X_), 'r--')

# plot data
plt.plot(X, y, 'bo')

# plot fitted line
y_ = regressor.predict(X_)
plt.plot(X_, y_, 'g-')
plt.show()
../_images/tutorials_02_neural_network_classifier_and_regressor_30_0.png

Regression with the Variational Quantum Regressor (VQR)

Similar to the VQC for classification, the VQR is a special variant of the NeuralNetworkRegressor with a OpflowQNN. By default it considers the L2Loss function to minimize the mean squared error between predictions and targets.

[24]:
vqr = VQR(feature_map=feature_map,
          ansatz=ansatz,
          optimizer=L_BFGS_B(),
          quantum_instance=quantum_instance,
          callback=callback_graph)
[25]:
# create empty array for callback to store evaluations of the objective function
objective_func_vals = []
plt.rcParams["figure.figsize"] = (12, 6)

# fit regressor
vqr.fit(X, y)

# return to default figsize
plt.rcParams["figure.figsize"] = (6, 4)

# score result
vqr.score(X, y)
../_images/tutorials_02_neural_network_classifier_and_regressor_33_0.png
[25]:
0.9761308715224429
[26]:
# plot target function
plt.plot(X_, f(X_), 'r--')

# plot data
plt.plot(X, y, 'bo')

# plot fitted line
y_ = vqr.predict(X_)
plt.plot(X_, y_, 'g-')
plt.show()
../_images/tutorials_02_neural_network_classifier_and_regressor_34_0.png
[27]:
import qiskit.tools.jupyter
%qiskit_version_table
%qiskit_copyright

Version Information

Qiskit SoftwareVersion
qiskit-terra0.18.3
qiskit-aer0.9.0
qiskit-machine-learning0.2.1
System information
Python3.8.12 (default, Sep 13 2021, 08:28:12) [GCC 9.3.0]
OSLinux
CPUs2
Memory (Gb)6.790924072265625
Wed Oct 06 18:43:56 2021 UTC

This code is a part of Qiskit

© Copyright IBM 2017, 2021.

This code is licensed under the Apache License, Version 2.0. You may
obtain a copy of this license in the LICENSE.txt file in the root directory
of this source tree or at http://www.apache.org/licenses/LICENSE-2.0.

Any modifications or derivative works of this code must retain this
copyright notice, and modified files need to carry a notice indicating
that they have been altered from the originals.