Version 1
: Received: 24 February 2021 / Approved: 24 February 2021 / Online: 24 February 2021 (12:55:28 CET)
How to cite:
Tan, M.; Xu, M.; Moss, D. Tera-OPs Photonic Convolutional Neural NetworksBased on Kerr Microcombs. Preprints2021, 2021020549. https://doi.org/10.20944/preprints202102.0549.v1
Tan, M.; Xu, M.; Moss, D. Tera-OPs Photonic Convolutional Neural NetworksBased on Kerr Microcombs. Preprints 2021, 2021020549. https://doi.org/10.20944/preprints202102.0549.v1
Tan, M.; Xu, M.; Moss, D. Tera-OPs Photonic Convolutional Neural NetworksBased on Kerr Microcombs. Preprints2021, 2021020549. https://doi.org/10.20944/preprints202102.0549.v1
APA Style
Tan, M., Xu, M., & Moss, D. (2021). Tera-OPs Photonic Convolutional Neural NetworksBased on Kerr Microcombs. Preprints. https://doi.org/10.20944/preprints202102.0549.v1
Chicago/Turabian Style
Tan, M., Mike Xu and David Moss. 2021 "Tera-OPs Photonic Convolutional Neural NetworksBased on Kerr Microcombs" Preprints. https://doi.org/10.20944/preprints202102.0549.v1
Abstract
Convolutional neural networks (CNNs), inspired by biological visual cortex systems, are a powerful category of artificial neural networks that can extract the hierarchical features of raw data to greatly reduce the network parametric complexity and enhance the predicting accuracy. They are of significant interest for machine learning tasks such as computer vision, speech recognition, playing board games and medical diagnosis [1-7]. Optical neural networks offer the promise of dramatically accelerating computing speed to overcome the inherent bandwidth bottleneck of electronics. Here, we demonstrate a universal optical vector convolutional accelerator operating beyond 10 Tera-OPS (TOPS - operations per second), generating convolutions of images of 250,000 pixels with 8-bit resolution for 10 kernels simultaneously — enough for facial image recognition. We then use the same hardware to sequentially form a deep optical CNN with ten output neurons, achieving successful recognition of full 10 digits with 900 pixel handwritten digit images with 88% accuracy. Our results are based on simultaneously interleaving temporal, wavelength and spatial dimensions enabled by an integrated microcomb source. This approach is scalable and trainable to much more complex networks for demanding applications such as unmanned vehicle and real-time video recognition.
Keywords
microcombs; neural networks
Subject
Engineering, Automotive Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
