[2] Princeton Univ, Dept Elect Engn, Princeton, NJ 08544 USA
[3] Univ British Columbia, Dept Elect & Comp Engn, Vancouver, BC V6T 1Z4, Canada
[4] George Washington Univ, Dept Elect & Comp Engn, V6T 1Z4, Washington, DC USA
来源:
2022 EUROPEAN CONFERENCE ON OPTICAL COMMUNICATION (ECOC)
|
2022年
关键词:
D O I:
暂无
中图分类号:
O43 [光学];
学科分类号:
070207 ;
0803 ;
摘要:
Photonics neural networks employ optical device physics for neuron models, and optical interconnects for distributed, parallel, and analog processing for high-bandwidth, low-latency, and low-switching energy applications in AI and neuromorphic computing. We discuss silicon photonics for machine learning acceleration for inference and in situ training. (c) 2022 The Author(s)
机构:
Acacia Commun, Adv Dev, Holmdel, NJ 07733 USA
US Air Force, Washington, DC USA
Bell Labs, 101 Crawford Corner Rd, Holmdel, NJ 07733 USAAcacia Commun, Adv Dev, Holmdel, NJ 07733 USA