Universal discriminative quantum neural networks

Recent results have demonstrated the successful applications of quantum-classical hybrid methods to train quantum circuits for a variety of machine learning tasks. A natural question to ask is consequentially whether we can also train such quantum circuits to discriminate quantum data, i.e., perform classification on data stored in form of quantum states. Although quantum mechanics fundamentally forbids deterministic discrimination of non-orthogonal states, we show in this work that it is possible to train a quantum circuit to discriminate such data with a trade-off between minimizing error rates and inconclusiveness rates of the classification tasks. Our approach achieves at the same time a performance which is close to the theoretically optimal values and a generalization ability to previously unseen quantum data. This generalization power hence distinguishes our work from previous circuit optimization results and furthermore provides an example of a quantum machine learning task that has inherently no classical analogue.

Automated summary

Recent research shows the success of training quantum circuits to classify quantum data despite the fundamental limitations of deterministic discrimination in quantum mechanics. By balancing error rates and inconclusiveness, the method achieves performance close to optimal values and generalizes well to unseen quantum data. This distinguishes the research from previous results and presents a unique quantum machine learning task without a classical analogue.