Photonic kernel machine learning for ultrafast spectral analysis

Abstract

We introduce photonic kernel machines, a scheme for ultrafast spectral analysis of noisy radio-frequency signals from single-shot optical intensity measurements. The approach combines the versatility of machine learning and the speed of photonic hardware to reach unprecedented throughput rates. We theoretically describe some of the key underlying principles, and then numerically illustrate the reached performances on a photonic lattice-based implementation. We apply the technique both to picosecond pulsed radio-frequency signals, on energy-spectral-density estimation and a shape classification task, and to continuous signals, on a frequency tracking task. The presented optical computing scheme is resilient to noise while requiring minimal control on the photonic-lattice parameters, making it readily implementable in realistic state-of-the-art photonic platforms.

19 pages, 11 figures. Final version accepted in PRApplied

References in corpus (8)

• Training and Operation of an Integrated Neuromorphic Network Based on Metal-Oxide Memristors
• Physical reservoir computing -- An introductory perspective
• Supervised quantum machine learning models are kernel methods
• Quantum federated learning through blind quantum computing
• Photonic extreme learning machine by free-space optical propagation
• Creating and concentrating quantum resource states in noisy environments using a quantum neural network
• Superpolynomial Quantum Enhancement in Polaritonic Neuromorphic Computing
• Equilibrium Propagation with Continual Weight Updates

Cited by in corpus (4)

• Noisy Quantum Kernel Machines
• Efficient estimation of trainability for variational quantum circuits
• Quantum Kernel Evaluation via Hong-Ou-Mandel Interference
• Machine learning via relativity-inspired quantum dynamics