Expressive power of parametrized quantum circuits
Yuxuan Du, Min-Hsiu Hsieh, Tongliang Liu, Dacheng Tao
Abstract
The authors demonstrate that parametrized quantum circuits possess a better expressive power than classical neural networks, such as restricted and deep Boltzmann machines. Based on the advanced expressive power, the authors propose a Bayesian quantum circuit that enables parametrized quantum circuits to perform machine learning tasks
Topics & Concepts
QuantumElectronic circuitComputer scienceBoltzmann machineQuantum circuitPower (physics)Quantum computerTheoretical computer scienceArtificial neural networkQuantum algorithmTopology (electrical circuits)AlgorithmExpressive powerScheme (mathematics)MathematicsQuantum systemRepresentation (politics)Feature (linguistics)Artificial intelligenceQuantum informationAlgebra over a fieldRestricted Boltzmann machineBayesian probabilityBoolean functionQuantum Computing Algorithms and ArchitectureQuantum many-body systemsMachine Learning in Materials Science