Benchmarking Neural Networks For Quantum Computations

• Published in: IEEE transaction on neural networks and learning systems 2020-07, Vol.31 (7), p.2522-2531
• Main Authors: Nguyen, Nam H., Behrman, E. C., Moustafa, Mohamed A., Steck, J. E.
• Format: Article
• Language: English
• Subjects: Algorithms; Benchmark testing; Benchmarking; Biological neural networks; complex neural network; complexity; Complexity theory; Computer simulation; Computers; entanglement; Learning algorithms; Machine learning; Neural networks; quantum computation; Quantum computers; Quantum computing; Quantum entanglement; quantum machine learning; quantum neural network
• ISSN: 2162-237X; 2162-2388
• DOI: 10.1109/TNNLS.2019.2933394

The power of quantum computers is still somewhat speculative. Although they are certainly faster than classical ones at some tasks, the class of problems they can efficiently solve has not been mapped definitively onto known classical complexity theory. This means that we do not know for which calculations there will be a "quantum advantage," once an algorithm is found. One way to answer the question is to find those algorithms, but finding truly quantum algorithms turns out to be very difficult. In previous work, over the past three decades, we have pursued the idea of using techniques of machine learning to develop algorithms for quantum computing. Here, we compare the performance of standard real- and complex-valued classical neural networks with that of one of our models for a quantum neural network, on both classical problems and on an archetypal quantum problem: the computation of an entanglement witness. The quantum network is shown to need far fewer epochs and a much smaller network to achieve comparable or better results.