Experimental kernel-based quantum machine learning in finite feature space
Abstract
We implement an all-optical setup demonstrating kernel-based quantum machine learning for two-dimensional classification problems. In this hybrid approach, kernel evaluations are outsourced to projective measurements on suitably designed quantum states encoding the training data, while the model training is processed on a classical computer. Our two-photon proposal encodes data points in a discrete, eight-dimensional feature Hilbert space. In order to maximize the application range of the deployable kernels, we optimize feature maps towards the resulting kernels’ ability to separate points, i.e., their “resolution,” under the constraint of finite, fixed Hilbert space dimension. Implementing these kernels, our setup delivers viable decision boundaries for standard nonlinear supervised classification tasks in feature space. We demonstrate such kernel-based quantum machine learning using specialized multiphoton quantum optical circuits. The deployed kernel exhibits exponentially better scaling in the required number of qubits than a direct generalization of kernels described in the literature.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Jul 23, 2020
- Source ID
- 10.1038/s41598-020-68911-5
Entities
People
- Antonín Černoch
- Clemens Gneiting
- Franco Nori
- Karel Lemr
- Karol Bartkiewicz
- Kateřina Jiráková
Organizations
- Army Research Office
- Czech Science Foundation
- Foundational Questions Institute
- Japan Science and Technology Agency
- Japan Society for the Promotion of Science
- Ministry of Education, Youth and Sports
- Palacký University Olomouc