Benchmarking neural networks for quantum computation

TL;DR

This paper compares classical and quantum neural networks, demonstrating that quantum networks can achieve similar or better results with fewer resources on classical and quantum problems.

Contribution

It introduces a quantum neural network model and benchmarks its performance against classical neural networks on relevant problems.

Findings

Quantum neural networks require fewer epochs to train.

Quantum networks achieve comparable or better accuracy.

Quantum networks use smaller architectures.

Abstract

The power of quantum computers is still somewhat speculative. While 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.