Graph kernel

Algorithm

Discrete mathematics

Physics

Kernel method

Support vector machine

Kernel embedding of distributions

Philosophy

Artificial intelligence

Pure mathematics

Qubit

Feature (linguistics)

Dimension (graph theory)

Mathematics

Computer science

Linguistics

Quantum computer

Quantum mechanics

Hilbert space

Kernel (algebra)

Theoretical computer science

Reproducing kernel Hilbert space

Feature vector

Quantum

Scientific Reports

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.

Experimental kernel-based quantum machine learning in finite feature space