Entanglement detection in pure states with a Quantum Classifier Algorithm
Quantum Computation, Machine Learning, Classification Algorithms, Quantum Entanglement
Entangled states proved to be an essential resource for information processing, however, its classification is still an open problem.
The objective of this work is to apply machine learning methods based on distance metrics to make a quantum state classification.
The classification method implementation was made using classical and quantum algorithms also comparing the performance and
efficiency of both. However, it should be noted that all quantum computation processes made in this work used simulators provided
by the SDK Qiskit. No real quantum computers were used to implement the quantum methods due to the qubit quantity that exceeds
the available open-access quantum computers of the IBM Q-Experience. The classical results obtained in this work make a good
classification of quantum states with a precision rate between $70\%$ and $80\%$. The quantum predictions may have a lower
precision, due to some simplifications made in the data pre-processing step, showing that quantum algorithms for entanglement
classification probably will require a higher number of qubits than the currently available ones.