Single photonic perceptron based on a soliton crystal Kerr microcomb for high-speed, scalable, optical neural networks
arXiv:2003.01347
Abstract
Optical artificial neural networks (ONNs), analog computing hardware tailored for machine learning, have significant potential for ultra-high computing speed and energy efficiency. We propose a new approach to architectures for ONNs based on integrated Kerr micro-comb sources that is programmable, highly scalable and capable of reaching ultra-high speeds. We experimentally demonstrate the building block of the ONN, a single neuron perceptron, by mapping synapses onto 49 wavelengths of a micro-comb to achieve a high single-unit throughput of 11.9 Giga-FLOPS at 8 bits per FLOP, corresponding to 95.2 Gbps. We test the perceptron 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 small wavelength spacing (49GHz) for a coherent integrated microcomb source, which results in an unprecedented number of wavelengths for neuromorphic optics. Finally, we propose an approach to scaling the perceptron to a deep learning network using the same single micro-comb 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 vehicle and aircraft tracking.
arXiv comment18 pages, 7 Figures, 62 References
References in corpus (29)
- Deep Learning with Coherent Nanophotonic Circuits
- All-Optical Machine Learning Using Diffractive Deep Neural Networks
- All-optical signal processing platforms for CMOS compatible integrated nonlinear optics
- Microresonator solitons for massively parallel coherent optical communications
- An Integrated-Photonics Optical-Frequency Synthesizer
- Fully integrated ultra-low power Kerr comb generation
- Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computing
- 1 Low power continuous-wave nonlinear optics in silica glass integrated waveguide structures
- Integrated micro-comb sources for quantum optical applications
- Harnessing optical micro-combs for microwave photonics
- Photonic RF and microwave reconfigurable filters and true time delays based on an integrated optical Kerr frequency comb source
- A Radio Frequency Channelizer based on Cascaded Integrated Micro-ring Resonator Optical Comb Sources and Filters
- Photonic radio frequency and microwave intensity differentiator based on an optical frequency comb source in an integrated micro-ring resonator
- High performance photonic microwave filters based on a 50GHz optical soliton crystal Kerr micro-comb
- Microwave photonic filters via radio frequency bandwidth scaling based on soliton crystal optical micro-combs
- Hilbert Transform based Quadrature Hybrid RF Photonic Coupler via a Micro-Resonator Optical Frequency Comb Source
- Novel architecture for ultra-stable micro-ring resonator based optical frequency combs
- Microwave and RF signal processing based on integrated soliton crystal optical microcombs
- Optical combs with a crystalline whispering gallery mode resonator
- Ultrafast modelocked nonlinear micro-cavity laser
- Ultra-pure RF tone from a micro-ring resonator based optical frequency comb source
- Microwave photonic fractional Hilbert transformer with an integrated optical soliton crystal micro-comb
- Phase-encoded RF signal generation based on an integrated 49GHz micro-comb optical source
- Parametric gain and wavelength conversion via third order nonlinear optics a CMOS compatible waveguide
- Microwave Q-band oscillator at 49GHz for broadband frequency conversion based on a Kerr optical soliton crystal micro-comb
- Optical Kerr soliton crystal microcomb source for RF photonic fractional differentiation
- Tunable RF and microwave photonic sideband generator based on cascaded 49GHz and 200GHz integrated ring resonators
- Microcomb-based true-time-delay network for microwave beamforming with arbitrary beam pattern control
- Human action recognition with a large-scale brain-inspired photonic computer