A review of quantum neural networks 2022 for generating learning tasks

Quantum computers are the next generation of computing devices that are expected to achieve computing tasks that classical computers cannot . Quantum machine learning , Especially quantum generative learning , Is one of the main ways to achieve this goal . Based on the inherent probability properties of quantum mechanics , We can reasonably assume that the quantum generative learning model （QGLM） It has the potential to surpass the learning ability of classical generative models . therefore , Quantum generative learning model has attracted more and more attention in quantum physics and computer science , The main work includes various quantum generative learning models that can be efficiently implemented on short-term quantum machines with potential computational advantages .

 

This paper summarizes the latest progress of quantum generative learning model from the perspective of machine learning . We interpret these quantum generative learning models as quantum extensions of classical generative learning models , Including quantum circuit born machine 、 Quantum generated countermeasure network 、 Quantum Boltzmann machine and quantum automatic encoder . In this context , We have explored the internal relations and fundamental differences between them . We further summarize the potential applications of quantum generative learning model in traditional machine learning tasks and quantum physics . Last , We discuss the challenges faced by the quantum generative learning model and the future research directions .

 

Thesis link ：https://arxiv.org/abs/2206.03066