Optical Neuromorphic Processor at 11 TeraOPs/s based on Kerr Soliton Crystal Micro-combs | |
Tan, Mengxi1; Xu, Xingyuan2; Wu, Jiayang1; Boes, Andreas3; Corcoran, Bill2; Nguyen, Thach G.3; Chu, Sai T.4; Little, Brent E.5; Hicks, Damien G.1,6; Morandotti, Roberto7; Mitchell, Arnan3; Moss, David J.1 | |
2022 | |
会议名称 | 2022 Optical Fiber Communications Conference and Exhibition, OFC 2022 |
会议录名称 | 2022 Optical Fiber Communications Conference and Exhibition, OFC 2022 - Proceedings |
会议日期 | 2022-03-06 |
会议地点 | San Diego, CA, United states |
出版者 | Institute of Electrical and Electronics Engineers Inc. |
产权排序 | 5 |
摘要 | We demonstrate a universal optical vector convolutional accelerator operating at 11 Tera-OPS, generating convolutions of images of 250,000 pixels with 8-bit resolution for 10 kernels simultaneously. We use the same hardware to form a deep optical CNN with ten output neurons, achieving successful recognition of full 10 digits with 88% accuracy. Our approach is scalable and trainable for applications to unmanned vehicle and real-time video recognition. © 2022 OSA. |
作者部门 | 瞬态光学研究室 |
收录类别 | EI ; CPCI |
ISBN号 | 9781557524669 |
语种 | 英语 |
WOS记录号 | WOS:000828152500064 |
EI入藏号 | 20221812050726 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/95871 |
专题 | 瞬态光学研究室 |
通讯作者 | Moss, David J. |
作者单位 | 1.Swinburne University of Technology, Optical Sciences Centre, Hawthorn; VIC, Australia; 2.Monash University, Department of Electrical and Computer Systems Engineering, Clayton; VIC, Australia; 3.Rmit University, School of Engineering, Melbourne; VIC, Australia; 4.City University of Hong Kong, Department of Physics, Hong Kong, Hong Kong; 5.Xi'an Institute of Optics and Precision Mechanics Precision Mechanics of Cas, Xi'an, China; 6.Bioinformatics Division, Walter and Eliza Hall Institute of Medical Research, Parkville; VIC, Australia; 7.Matériaux et Télécommunications, INRS-Énergie, Varennes; QC, Canada |
推荐引用方式 GB/T 7714 | Tan, Mengxi,Xu, Xingyuan,Wu, Jiayang,et al. Optical Neuromorphic Processor at 11 TeraOPs/s based on Kerr Soliton Crystal Micro-combs[C]:Institute of Electrical and Electronics Engineers Inc.,2022. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Optical Neuromorphic(615KB) | 会议论文 | 限制开放 | CC BY-NC-SA | 请求全文 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论