OpflowQNN; Quantum Neural Networks【Qiskit】

Assumption

Environments

• JupyterNotebook
• python3

About neural network

The NeuralNetwork represents the interface for all neural networks available in Qiskit Machine Learning. It exposes a forward and a backward pass taking the data samples and trainable weights as input. A NeuralNetwork does not contain any training capabilities, these are pushed to the actual algorithms / applications. Thus, a NeuralNetwork also does not store the values for trainable weights. In the following, different implementations of this interfaces are introduced.

What is Opflow QNN

Opflow Quantum Neural Network.

Instllation

$ pip install qiskit_machine_learning

Setting

import numpy as np

from qiskit import Aer, QuantumCircuit
from qiskit.circuit import Parameter
from qiskit.circuit.library import RealAmplitudes, ZZFeatureMap
from qiskit.opflow import StateFn, PauliSumOp, AerPauliExpectation, ListOp, Gradient
from qiskit.utils import QuantumInstance, algorithm_globals

algorithm_globals.random_seed = 42
expval = AerPauliExpectation()
gradient = Gradient()
qi_sv = QuantumInstance(Aer.get_backend("aer_simulator_statevector"))
qi_qasm = QuantumInstance(Aer.get_backend("aer_simulator"), shots=10)

Suppose a NeuralNetwork called nn. Then, the nn.forward(input, weights) pass takes either flat inputs for the data and weights of size nn.num_inputs and nn.num_weights, respectively. NeuralNetwork supports batching of inputs and returns batches of output of the corresponding shape.

Coding

from qiskit_machine_learning.neural_networks import OpflowQNN

params1 = [Parameter("input1"), Parameter("weight1")]
qc1 = QuantumCircuit(1)
qc1.h(0)
qc1.ry(params1[0], 0)
qc1.rx(params1[1], 0)
qc_sfn1 = StateFn(qc1)

H1 = StateFn(PauliSumOp.from_list([("Z", 1.0), ("X", 1.0)]))

op1 = ~H1 @ qc_sfn1
print(op1)

↓ Out

qnn1 = OpflowQNN(op1, [params1[0]], [params1[1]], expval, gradient, qi_sv)

input1 = algorithm_globals.random.random(qnn1.num_inputs)
weights1 = algorithm_globals.random.random(qnn1.num_weights)

qnn1.forward(input1, weights1)

↓Out

qnn1.backward(input1, weights1)

↓Out

qnn1.backward([input1, input1], weights1)

↓Out

op2 = ListOp([op1, op1])
qnn2 = OpflowQNN(op2, [params1[0]], [params1[1]], expval, gradient, qi_sv)

qnn2.forward(input1, weights1)

↓Out

Result