Photonic Perceptron Based on a Kerr Microcomb for High‐Speed, Scalable, Optical Neural Networks
Xingyuan Xu, Mengxi Tan, Bill Corcoran, Jiayang Wu, Thach G. Nguyen, Andreas Boes, Sai T. Chu, Brent E. Little, Roberto Morandotti, Arnan Mitchell, D. G. Hicks, David Moss
Abstract
Abstract Optical artificial neural networks (ONNs)—analog computing hardware tailored for machine learning—have significant potential for achieving ultra‐high computing speed and energy efficiency. A new approach to architectures for ONNs based on integrated Kerr microcomb sources that is programmable, highly scalable, and capable of reaching ultra‐high speeds is proposed here. The building block of the ONN—a single neuron perceptron—is experimentally demonstrated that reaches a high single‐unit throughput speed of 11.9 Giga‐FLOPS at 8 bits per FLOP, corresponding to 95.2 Gbps, achieved by mapping synapses onto 49 wavelengths of a microcomb. The perceptron is tested on simple standard benchmark datasets—handwritten‐digit recognition and cancer‐cell detection—achieving over 90% and 85% accuracy, respectively. This performance is a direct result of the record low wavelength spacing (49 GHz) for a coherent integrated microcomb source, which results in an unprecedented number of wavelengths for neuromorphic optics. Finally, an approach to scaling the perceptron to a deep learning network is proposed using the same single microcomb device and standard off‐the‐shelf telecommunications technology, for high‐throughput operation involving full matrix multiplication for applications such as real‐time massive data processing for unmanned vehicles and aircraft tracking.