Experimental kernel-based quantum machine learning in finite feature space
arXiv:1906.04137 · doi:10.1038/s41598-020-68911-5
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.
5 pages, 3 figures
References in corpus (12)
- Supervised learning with quantum enhanced feature spaces
- An introduction to quantum machine learning
- Extending the computational reach of a noisy superconducting quantum processor
- An Artificial Neuron Implemented on an Actual Quantum Processor
- Experimental Realization of Quantum Artificial Intelligence
- Machine Learning in Electronic Quantum Matter Imaging Experiments
- Machine Learning for Optimal Parameter Prediction in Quantum Key Distribution
- Computational speedups using small quantum devices
- Detecting entanglement in spatial interference
- A machine learning approach to dynamical properties of quantum many-body systems
- Optimizing High-Efficiency Quantum Memory with Quantum Machine Learning for Near-Term Quantum Devices
- Experimental measurement of Hilbert-Schmidt distance between two-qubit states as means for speeding-up machine learning