Machine learning for adaptive quantum measurement

The talk presents an example based introduction on how machine learning can be applied to a quantum system. It starts with illustrating the main concepts of quantum information science and points out essential differences between classical and quantum systems, which are important in designing AI systems. The main part of the talk is dedicated to the application of machine learning to adaptive quantum measurements which is important for atomic clocks and gravitational wave detection. I present a machine learning algorithm, which is based on particle swarm optimization, that learns how to perform optimal phase measurements based on experimental trial runs, which can be either simulated or performed using a real world experiment. Our algorithm does not require prior knowledge about the physical processes involved.