Journal
SCIENTIFIC REPORTS
Volume 11, Issue 1, Pages -Publisher
NATURE PORTFOLIO
DOI: 10.1038/s41598-021-82543-3
Keywords
-
Categories
Funding
- U.S. Army Research Office through the Institute for Soldier Nanotechnologies (ISN) at MIT [W911NF-18-2-0048]
- Natural Sciences and Engineering Research Council of Canada
- National Science Foundation (NSF) E2CDA Grant [1640012]
- ISN Grant
- NSF Graduate Research Fellowship Program [1122374]
- NTT Research Inc.
- NSF EAGER program [1946967]
- NSF/SRC E2CDA
- Intelligence Community Postdoctoral Research Fellowship at MIT
- ISN
Ask authors/readers for more resources
The article discusses the trend of growing deep neural network models for higher accuracy and complexity, proposing a digital optical neural network (DONN) to overcome scaling limitations of traditional processors. Experimental results show that optical multicast is effective in image classification.
As deep neural network (DNN) models grow ever-larger, they can achieve higher accuracy and solve more complex problems. This trend has been enabled by an increase in available compute power; however, efforts to continue to scale electronic processors are impeded by the costs of communication, thermal management, power delivery and clocking. To improve scalability, we propose a digital optical neural network (DONN) with intralayer optical interconnects and reconfigurable input values. The path-length-independence of optical energy consumption enables information locality between a transmitter and a large number of arbitrarily arranged receivers, which allows greater flexibility in architecture design to circumvent scaling limitations. In a proof-of-concept experiment, we demonstrate optical multicast in the classification of 500 MNIST images with a 3-layer, fully-connected network. We also analyze the energy consumption of the DONN and find that digital optical data transfer is beneficial over electronics when the spacing of computational units is on the order
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available