Affiliation:
1. Department of Electrical and Computer Engineering Princeton University Princeton NJ 08540 USA
2. Optical Networking & Sensing NEC Laboratories America Princeton NJ 08540 USA
3. Department of Physics Engineering Physics & Astronomy Queen's University Kingston Ontario K7M 3N6 Canada
Abstract
Broadband analog signal processors utilizing silicon photonics have demonstrated a significant impact in numerous application spaces, offering unprecedented bandwidths, dynamic range, and tunability. In the past decade, microwave photonic techniques have been applied to neuromorphic processing, resulting in the development of novel photonic neural network architectures. Neuromorphic photonic systems can enable machine learning capabilities at extreme bandwidths and speeds. Herein, low‐quality factor microring resonators are implemented to demonstrate broadband optical weighting. In addition, silicon photonic neural network architectures are critically evaluated, simulated, and optimized from a radio‐frequency performance perspective. This analysis highlights the linear front‐end of the photonic neural network, the effects of linear and nonlinear loss within silicon waveguides, and the impact of electrical preamplification.
Funder
National Science Foundation
Reference55 articles.
1. Microwave photonics combines two worlds
2. Microwave Photonics
3. Limits on the performance of RF-over-fiber links and their impact on device design
4. E. I.Ackerman C. H.Cox inMicrowave Photonics (MWP) and the 2014 9th Asia‐Pacific Microwave Photonics Conf. (APMP) 2014 Int. Topical Meeting on IEEE Hokkaido Japan October2014 pp.430–433.
5. Integrated microwave photonics