Quantum Machine Learning
Introduction
Nowadays, a general purpose quantum computer seems closer to reality than ever before, yet, it is so far. Quantum Computing truly has the potential but, when will it live up to the (rising) expectations? Can the near-term quantum technologies create an impact on ML and guide us towards quantum supremacy? There has been a steady progress in this field, from increasing qubits to the increase in algorithms and design techniques. Popular quantum com- puting algorithms, e.g, Shor’s algorithm, Grover’s algorithm, Deutsch-Jozsa, BB84 Protocol, Quantum Fourier Transform and others have all been instrumental achievements in their fields. But in Machine Learning there is no such defining al- gorithm yet. Is their a feasible Quantum Approach for Machine Learning (ML) in near-term future? The estimated number of qubits in near-term future is 100-1000 which unfortunately is not sufficient for large ML tasks. This report contains an introduction to machine learning and quatum mechanics. We also discuss a quantum algorithm to solve linear system of equations and then moves onto discussing Quantum-Assisted Machine Learning on a very promising field of unsupervised ML, its the opportunities and challenges in the near-term future.
The report can be viewed here.
The slides with pauses can be viewed here.
The slides without pauses can be viewed here.
TeX-nical Details
This is the primary TeX file which is to be compiled to get the report.
This is the BibTeX file containing the references used by me.