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

Nota

Questa pagina è stata generata da docs/tutorials/02_neural_network_classifier_and_regressor.ipynb.

Neural Network Classifier & Regressor

In questo tutorial mostriamo come vengono utilizzati NeuralNetworkClassifier e NeuralNetworkRegressor. Entrambi accettano come input una NeuralNetwork (quantistica), e la sfruttano in un contesto specifico. In entrambi i casi forniamo, per comodità, anche una variante pre-configurata, il Variational Quantum Classifier (VQC) ed il Variational Quantum Regressor (VQR). Il tutorial è strutturato come segue:

  1. Classificazione

    • Classificazione con un OpflowQNN

    • Classificazione con CircuitQNN

    • Variational Quantum Classifier (VQC)

  2. Regressione

    • Regressione con un 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)

Classificazione

Per illustrare i seguenti algoritmi, prepariamo un semplice dataset per la classificazione.

[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

Classificazione con un OpflowQNN

Per prima cosa mostriamo come un OpflowQNN può essere utilizzato per la classificazione con NeuralNetworkClassifier. In questo contesto, OpflowQNN dovrebbe restituire un output unidimensionale in \([-1, +1]\). Questo funziona solo per la classificazione binaria, e quindi assegniamo le due classi a \(\{-1, +1\}\). Per comodità, usiamo la TwoLayerQNN, la quale è un tipo speciale di OpflowQNN definita tramite una feature map ed un 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([[0.47265625]])

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]:
0.5
[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

Classificazione con CircuitQNN

Successivamente mostriamo come si può utilizzare CircuitQNN per una classificazione con NeuralNetworkClassifier. In questo contesto, CircuitQNN deve restituire come output un vettore di probabilità \(d\)-dimensionale, dove \(d\) indica il numero di classi. Campionare da un QuantumCircuit risulta automaticamente in una distribuzione di probabilità, e dobbiamo solo definire una mappatura delle bitstring misurate nelle diverse classi. Per la classificazione binaria usiamo la mappatura di parità.

[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]:
0.65
[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)

VQC è una variante particolare del NeuralNetworkClassifier con un CircuitQNN. Applica una mappa di parità (o estensioni a più classi) per mappare la bitstring alla classificazione, cosa che si traduce in un vettore di probabilità interpretato come un risultato codificato con il metodo one-hot encoding. Di default, il VQC applica la funzione CrossEntropyLoss che si aspetta i label in formato one-hot encoded e restituirà anche le previsioni in quel formato.

[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]:
0.6
[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

Regressione

Per illustrare i seguenti algoritmi prepariamo un semplice dataset su cui eseguire un metodo di regressione.

[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

Regressione con un OpflowQNN

Qui ci limitiamo alla regressione con un OpflowQNN che restituisce valori in \([-1, +1]\). Si potrebbero costruire modelli più complessi e anche multidimensionali, sempre basati su CircuitQNN, ma questo va oltre l’ambito di questo 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]:
0.9696567935175576
[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

Regressione con il Variational Quantum Regressor (VQR)

Come nel caso del VQC per la classificazione, il VQR è una variante speciale del NeuralNetworkRegressor con un OpflowQNN. Di default, il VQR utilizza la funzione L2Loss per minimizzare l’errore quadratico medio tra predizioni e target.

[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]:
0.9684356876095139
[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-terra0.19.0.dev0+803bd0d
qiskit-aer0.8.2
qiskit-machine-learning0.3.0
System information
Python3.9.6 (default, Aug 18 2021, 15:44:49) [MSC v.1916 64 bit (AMD64)]
OSWindows
CPUs4
Memory (Gb)11.83804702758789
Sun Aug 29 01:09:16 2021 Hora de verano romance

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.