1
$\begingroup$

I'm working on QSVM to know the difference between SVM and QSVM. How much better quantum machine learning can do when compared to classical machine learning algorithms?

Part of my code:

backend = BasicAer.get_backend('qasm_simulator', hub=None)
quantum_instance = QuantumInstance(backend, shots=1024, seed=seed, 
                                     seed_transpiler=seed)
result = qsvm.run(quantum_instance) 
print("test accuracy: ", result['testing_accuracy'])

With the above code, I can get the accuracy of the test.

I'm trying to know whether I can draw a decision boundary and classify results from QSVM just like how classical SVM does.

print(result.keys())

    dict_keys(['svm', 'kernel_matrix_testing', 'test_success_ratio', 'kernel_matrix_training', 'testing_accuracy'])

print (result['svm'].keys())

    dict_keys(['bias', 'alphas', 'support_vectors', 'yin'])

Given only these are the keys that result has, how can I look at QSVM results into two classes graphically? I could get the prediction results though! my new_test_data= 2d array to classify between these two classes : good=1/ bad=0

predictions = qsvm.predict(new_test_data,quantum_instance)
print(predictions)
    [1 0 0 0 0 0 0 0 1 1 0 1 1 0 1 0]

Given I don't see how get decision function and be able to plot decision boundary and margins? Like this as we do in classical SVM:

Any help in clarifying how to read the results to plot a graph like this from running QSVM would be much appreciated.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.