Speaker
Mr
Kosuke Mitarai
(Osaka University)
Description
We propose a classical-quantum hybrid algorithm for machine learning on near-term quantum processors, which we call quantum circuit learning. A quantum circuit driven by our framework learns to perform a given task by tuning parameters implemented on it. We also provide a way to obtain an analytical gradient of an expectation value of an observable for gradient-beased optimization of parameters. Theoretical investigation shows that a quantum circuit can approximate nonlinear functions, which is further confirmed by numerical simulations. Quantum circuits can provide feature maps that have not been accessible with classical approach. Hybridizing a low-depth quantum circuit and a classical computer for machine learning.
Primary author
Mr
Kosuke Mitarai
(Osaka University)
Co-authors
Dr
Keisuke Fujii
(Kyoto University)
Dr
Makoto Negoro
(Osaka University)
Prof.
Masahiro Kitagawa
(Osaka University)
