Photonic convolutional accelerator and neural network in the Tera-OPs regime based on soliton crystal Kerr microcombs
Mengxi Tan, Xingyuan Xu, Jiayang Wu, Andreas Boes, Bill Corcoran, Thach Giang Nguyen, S. T. Chu, Brent E. Little, Roberto Morandotti, Arthur James Lowery, Arnan Mitchell, Damien G. Hicks, David Moss · OSA Advanced Photonics Congress 2021 · 2021
We report a new approach to ONNs based on integrated Kerr micro-combs that is programmable, highly scalable and capable of reaching ultra-high speeds. We demonstrate a single neuron perceptron at 11.9 Giga-OPS at 8 bits per OP, or 95.2 Gbps. We then demonstrate a convolutional accelerator operating beyond 11 TeraOPs/s. We test the perceptron on handwritten-digit recognition and cancer-cell detection — achieving over 90% and 85% accuracy, respectively.