Quantum Kerr Learning

Abstract Quantum machine learning is a rapidly evolving field of research that could facilitate important applications for quantum computing and also significantly impact data-driven sciences. In our work, based on various arguments from complexity theory physics, we demonstrate single Kerr mode can provide some ‘quantum enhancements’ when dealing with kernel-based methods. Using kernel properties, neural tangent theory, first-order perturbation the non-linearity, non-perturbative numerical simulations, show enhancements happen in terms convergence time generalization error. Furthermore, make explicit indications how higher-dimensional input data be considered. Finally, propose an experimental protocol, call , circuit QED.